nrimsky / LM-expLinks
LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
☆94Updated last year
Alternatives and similar repositories for LM-exp
Users that are interested in LM-exp are comparing it to the libraries listed below
Sorting:
- Steering Llama 2 with Contrastive Activation Addition☆158Updated last year
- General-purpose activation steering library☆78Updated last month
- Algebraic value editing in pretrained language models☆65Updated last year
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆72Updated 3 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆108Updated 4 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆98Updated 4 months ago
- A resource repository for representation engineering in large language models☆126Updated 7 months ago
- A library for efficient patching and automatic circuit discovery.☆67Updated 2 months ago
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆81Updated last year
- Function Vectors in Large Language Models (ICLR 2024)☆170Updated 2 months ago
- ☆85Updated 10 months ago
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆78Updated last year
- ☆131Updated 7 months ago
- ☆226Updated 8 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆109Updated last year
- ☆44Updated last year
- Improving Alignment and Robustness with Circuit Breakers☆214Updated 9 months ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆121Updated this week
- Sparse probing paper full code.☆58Updated last year
- Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization☆26Updated 10 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 7 months ago
- ☆173Updated 2 months ago
- ☆35Updated last month
- AI Logging for Interpretability and Explainability🔬☆123Updated last year
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆58Updated 2 weeks ago
- ☆213Updated last year
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆20Updated 7 months ago
- ☆95Updated last year
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆60Updated 6 months ago
- Using sparse coding to find distributed representations used by neural networks.☆255Updated last year