A CLI tool for analyzing Claude Code/Codex CLI usage from local JSONL files.

Allow LLMs to control a browser with Browserbase and Stagehand

AllenAI's post-training codebase

Open source replication of Anthropic's Crosscoders for Model Diffing

Code for running RFdiffusion

AlphaFold Meets Flow Matching for Generating Protein Ensembles

The hub for EleutherAI's work on interpretability and learning dynamics

METR Task Standard

Steering Llama 2 with Contrastive Activation Addition

The nnsight package enables interpreting and manipulating the internals of deep learned models.

Code for reproducing our paper "Not All Language Model Features Are Linear"

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

Training Sparse Autoencoders on Language Models

Using sparse coding to find distributed representations used by neural networks.

Sparse probing paper full code.

Accessible large language models via k-bit quantization for PyTorch.

Convenience functions for working with pytorch hooks.

Solve puzzles. Improve your pytorch.

Interpreting how transformers simulate agents performing RL tasks

Graph-based LLM power tool for exploring many completions in parallel.

LlamaIndex is the leading framework for building LLM-powered agents over your data.

High-speed download of LLaMA, Facebook's 65B parameter GPT model