Mapping the Mind of a Large Language Model(anthropic.com)

132 points by Josely 2 years ago | 52 comments

Tracing the thoughts of a large language model(anthropic.com)

987 points by Philpax 1 year ago | 356 comments

Anthropic research post from March 2025 describing interpretability work that traces the internal computations of its Claude language model.

LLMs use a surprisingly simple mechanism to retrieve some stored knowledge(news.mit.edu)

336 points by CharlesW 2 years ago | 121 comments

MIT News article on research showing LLMs often retrieve stored facts via simple linear functions, and a technique to probe what a model knows about subjects.

Alignment faking in large language models(anthropic.com)

281 points by adultorata 1 year ago | 316 comments

Decomposing language models into understandable components(anthropic.com)

402 points by tompark 3 years ago | 58 comments

Anthropic research post from Oct 2023 on decomposing language model neurons into more interpretable features.

Signs of introspection in large language models(anthropic.com)

152 points by themgt 1 year ago | 88 comments