{"schemaVersion":"nuwa-current-record-1","version":"2026-10-29.1","publication":"published","work":{"id":"activation-oracles","title":"Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers","aliases":[],"authors":["Adam Karvonen","James Chua","Clément Dumas","Kit Fraser-Taliente","Subhash Kantamneni","Julian Minder","Euan Ong","Arnab Sen Sharma","Daniel Wen","Owain Evans","Samuel Marks"],"primaryFunction":"evaluation","secondaryFunctions":[],"kind":"method","sourceId":"activation-oracles-publication","attributionSourceId":"activation-oracles-publication","originalUrl":"https://truthful.ai/papers/activation-oracles/","publicationDate":"2025-12-19","updatedOn":"2026-10-25","areas":["deception"],"scopeNote":{"en":"Relevance is assigned to the research question and stated conditions of the work. A topic tag is not a risk rating.","zh":"风险关联依据研究问题及明确条件建立，主题标签不代表风险评级。"},"protocolIds":[],"contributions":[{"organizationId":"truthful","role":"publisher","sourceId":"activation-oracles-publication","locator":"Official publication masthead and article byline"}],"summary":{"en":"Trains models to answer questions about another model’s activations and evaluates generalization to hidden information and goals.","zh":"训练模型回答关于另一模型激活的问题，并评测其对隐藏信息与目标的泛化。"},"note":{"question":null,"method":null,"finding":null,"supports":null,"limits":null,"connections":null},"resources":[],"noteStatus":{"question":"limited","method":"limited","finding":"limited","supports":"limited","limits":"limited","connections":"limited"},"noteAvailability":{"en":"A substantive NUWA research note is not yet available. The repeated draft sections were removed pending review of the original methods, findings and limitations; use the original publication for the research account.","zh":"实质性的 NUWA 研究笔记尚未完成。重复草稿章节已移除，待核查原始方法、发现与限制；研究内容请以原始出版物为准。"},"noteSourceLocator":"No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence.","tags":["risk-monitoring"]},"reading":{"id":"activation-oracles","title":"Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers","en":{"question":"Can a language-model interface interpret activations across downstream auditing tasks?","design":"Oracles receive target-model activations and natural-language questions, trained on system prompts, classification and self-supervised context prediction.","findings":["The article reports generalization to secret information and fine-tuned goals absent from the training tasks.","More diverse supervision improved accuracy in ablations across four model families."],"interpretation":"NUWA interpretation: activation QA can reuse an interface across audits, but answers remain model-generated interpretations.","limits":"The short author article does not establish universal cross-model validity, adversarial robustness or guaranteed access to model beliefs.","decisionRelevance":"Model recommendation: validate each downstream audit with held-out ground truth and retain target/oracle identities.","takeaway":"NUWA interpretation: activation QA can reuse an interface across audits, but answers remain model-generated interpretations.","connections":[],"scoring":null,"conditions":null,"statistics":null,"usage":"Model recommendation: validate each downstream audit with held-out ground truth and retain target/oracle identities."},"zh":{"question":"语言模型接口能否跨审计任务解释激活？","design":"预言器接收目标激活与自然语言问题，用系统提示、分类及自监督上下文预测训练。","findings":["作者文章报告泛化至训练未含的秘密信息与微调目标。","四模型族消融中更多样监督提高正确率。"],"interpretation":"NUWA 解读：激活问答可复用接口，但回答仍是模型生成解释。","limits":"简短作者介绍未确立通用跨模型效度、抗对抗能力或信念访问保证。","decisionRelevance":"模型建议：每项下游审计以保留真值验证，并保留目标与预言器身份。","takeaway":"NUWA 解读：激活问答可复用接口，但回答仍是模型生成解释。","connections":[],"scoring":null,"conditions":null,"statistics":null,"usage":"模型建议：每项下游审计以保留真值验证，并保留目标与预言器身份。"},"assertionPolicy":{"question":"source-research-question","design":"source-finding","findings":"source-finding","interpretation":"nuwa-interpretation","limits":"source-limit-or-explicit-editorial-scope-limit","connections":"source-supported-relationship-only","decisionRelevance":"model-recommendation-not-source-conclusion"},"sourceRefs":[{"sourceId":"activation-oracles-publication","url":"https://truthful.ai/papers/activation-oracles/","locator":"Abstract","version":"Selected original resource https://truthful.ai/papers/activation-oracles/; sha256:e57df5c8ebc075889e7fd15723a7f00ff4c789a4d6be58f4899631bb9b50e6e2; archived source capture; exact capture time not independently established","artifactSha256":"e57df5c8ebc075889e7fd15723a7f00ff4c789a4d6be58f4899631bb9b50e6e2"},{"sourceId":"activation-oracles-publication","url":"https://truthful.ai/papers/activation-oracles/","locator":"Method","version":"Selected original resource https://truthful.ai/papers/activation-oracles/; sha256:e57df5c8ebc075889e7fd15723a7f00ff4c789a4d6be58f4899631bb9b50e6e2; archived source capture; exact capture time not independently established","artifactSha256":"e57df5c8ebc075889e7fd15723a7f00ff4c789a4d6be58f4899631bb9b50e6e2"},{"sourceId":"activation-oracles-publication","url":"https://truthful.ai/papers/activation-oracles/","locator":"Activation Oracles generalize to downstream auditing tasks","version":"Selected original resource https://truthful.ai/papers/activation-oracles/; sha256:e57df5c8ebc075889e7fd15723a7f00ff4c789a4d6be58f4899631bb9b50e6e2; archived source capture; exact capture time not independently established","artifactSha256":"e57df5c8ebc075889e7fd15723a7f00ff4c789a4d6be58f4899631bb9b50e6e2"},{"sourceId":"activation-oracles-publication","url":"https://truthful.ai/papers/activation-oracles/","locator":"How does Activation Oracle training scale?","version":"Selected original resource https://truthful.ai/papers/activation-oracles/; sha256:e57df5c8ebc075889e7fd15723a7f00ff4c789a4d6be58f4899631bb9b50e6e2; archived source capture; exact capture time not independently established","artifactSha256":"e57df5c8ebc075889e7fd15723a7f00ff4c789a4d6be58f4899631bb9b50e6e2"}],"publication":{"state":"published","publishedOn":"2026-10-29","authorizationReference":"user-authorized-global-index-publication-2026-10-29","reviewedCandidateId":"local-6efe31bc4a0c0f37"},"review":{"state":"published-note","sourceScope":"full-text","availableScope":null,"readingCoverage":"selected-source-sections; not a complete section-by-section paper audit","completePaperAudit":false,"independentEvidenceReview":"pending-human-review","bilingualEditorialReview":"pending-human-review","authorship":"model-assisted-research-note","preparedFingerprint":"887d17389b68f83c26120d1cf74e9ad17a1c9f5d3045aff641bd36a225f51e8a"}},"sources":[{"id":"activation-oracles-publication","title":"Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers","url":"https://truthful.ai/papers/activation-oracles/","version":"Source capture 2026-10-25","publicationDate":"2025-12-19","datePrecision":"day","type":"research-publication","verifiedOn":"2026-10-25","documentId":"https://truthful.ai/papers/activation-oracles","authors":["Adam Karvonen","James Chua","Clément Dumas","Kit Fraser-Taliente","Subhash Kantamneni","Julian Minder","Euan Ong","Arnab Sen Sharma","Daniel Wen","Owain Evans","Samuel Marks"]}]}