[NeurIPS 2025 Spotlight] Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning.

Processed / Cleaned Data for Paper Copilot

Code for Learning to Interpret Weight Differences in Language Models (Goel et al. 2025)

A Unified Framework for High-Performance and Extensible LLM Steering

Persona Vectors: Monitoring and Controlling Character Traits in Language Models

The best ChatGPT that $100 can buy.

This repo contains the source code for the paper "Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning"

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

[NeurIPS'25] Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders

Enhancing Automated Interpretability with Output-Centric Feature Descriptions

LaTeX files for the Deep Learning book notation

Config files for mixer

tmux source code

Lightweight clipboard manager for macOS

AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models, ICLR 2025 (Outstanding Paper)

ZJU RVPN 客户端的 Go 语言实现

A technique for removing sleeper agent behavior

This repository collects all relevant resources about interpretability in LLMs

awesome papers in LLM interpretability

Color palettes for Python

Research papers about Chain of Thought (CoT)

Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

Measuring Massive Multitask Language Understanding | ICLR 2021

Stanford NLP Python library for Representation Finetuning (ReFT)