Stanford NLP Python library for understanding and improving PyTorch models via interventions

This repository collects all relevant resources about interpretability in LLMs

Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.

From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous batching, speculative decoding, a Rust gateway, a JAX oracle, and interpretability tooling.

A curated collection of resources focused on the Mechanistic Interpretability (MI) of Large Multimodal Models (LMMs). This repository aggregates surveys, blog posts, and research papers that explore how LMMs represent, transform, and align multimodal information internally.

Stanford NLP Python library for benchmarking the utility of LLM interpretability methods

Steering vectors for transformer language models in Pytorch / Huggingface

Decomposing and Editing Predictions by Modeling Model Computation

Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interpretability on sleeper agents, and agent integration via CLI wrappers

Unified access to Large Language Model modules using NNsight

A carefully curated collection of high-quality libraries, projects, tutorials, research papers, and other essential resources focused on Mechanistic Interpretability, a growing subfield in machine learning interpretability research that aims to reverse-engineer neural networks into understandable computational components.

Mechanistically interpretable neurosymbolic AI (Nature Comput Sci 2024): losslessly compressing NNs to computer code and discovering new algorithms which generalize out-of-distribution and outperform human-designed algorithms

[ICLR 2025] Code and Data Repo for Paper "Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation"

A Mechanistic Interpretability Toolkit for Cross-Layer Transcoder Training and Attribution-Graph Visualization

Interpreting how transformers simulate agents performing RL tasks

Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".

🧠 Starter templates for doing interpretability research

Automatically extract executable programs from pruned mechanistic circuits, extending OpenAI's Sparse Circuits

Sparse probing paper full code.

Generating and validating natural-language explanations for the brain.