{"id":"url:anthropic.com/research/tracing-thoughts-language-model","title":"Tracing thoughts of a language model / Circuit tracing (Anthropic)","date":"2025-03-27","section":"AI safety and consciousness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/6817b4eca1b10533ef10b19c81e7c61b3877f963641fea2a81c5a46f68a233cf/","source_url":"https://www.anthropic.com/research/tracing-thoughts-language-model","text_available":false,"authors":[],"outgoing":[{"source":"url:anthropic.com/research/tracing-thoughts-language-model","target":"url:transformer-circuits.pub/2025/attribution-graphs/biology.html","evidence":"url","id":"url:transformer-circuits.pub/2025/attribution-graphs/biology.html","title":"Attribution graphs, the biology of the model","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8b3e14c537e89eed9a4402e9c14094d69913ed24d45fdab1a82ba4b8280660e2/"},{"source":"url:anthropic.com/research/tracing-thoughts-language-model","target":"url:transformer-circuits.pub/2025/attribution-graphs/methods.html","evidence":"url","id":"url:transformer-circuits.pub/2025/attribution-graphs/methods.html","title":"Circuit tracing / attribution graphs (methods)","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/7d4ba254716fd13d3a1ffb6518788e304eaa7077bd9d7bce201094eb293518b4/"}],"incoming":[{"source":"url:ai-2027.com","target":"url:anthropic.com/research/tracing-thoughts-language-model","evidence":"url","id":"url:ai-2027.com","title":"AI 2027 (Kokotajlo)","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/3fd447e0ff58689ae00a4666e28bbd7faecd472dec7195ab1d524cb5402a1766/"}],"text_parts":[],"contents":[],"text_code_points":0,"source_markdown":null}