zjunlp/Mechanist

A library for mechanistic interpretability of GPT-style language models

🪄 Interpreto is an interpretability toolbox for LLMs

A curated list of Large Language Model (LLM) Interpretability resources.

Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models know themselves through automated interpretability.

To know what models don't say out loud.

Awesome paper in LLM Psychometrics and LLM Psychology

Keeping language models honest by directly eliciting knowledge encoded in their activations.

web app for chatting with llms on openrouter with leaked unabridged reasoning

LLM Transparency Tool (LLM-TT), an open-source interactive toolkit for analyzing internal workings of Transformer-based language models. *Check out demo at* https://huggingface.co/spaces/facebook/llm-transparency-tool-demo