nrimsky / CAALinks
Steering Llama 2 with Contrastive Activation Addition
☆158Updated last year
Alternatives and similar repositories for CAA
Users that are interested in CAA are comparing it to the libraries listed below
Sorting:
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆94Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆108Updated 4 months ago
- General-purpose activation steering library☆78Updated last month
- ☆131Updated 7 months ago
- ☆173Updated 2 months ago
- Algebraic value editing in pretrained language models☆65Updated last year
- ☆85Updated 10 months ago
- ☆226Updated 8 months ago
- Using sparse coding to find distributed representations used by neural networks.☆255Updated last year
- A library for efficient patching and automatic circuit discovery.☆67Updated 2 months ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆121Updated this week
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆72Updated 3 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆170Updated 2 months ago
- ☆101Updated 3 weeks ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 7 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆185Updated this week
- A resource repository for representation engineering in large language models☆126Updated 7 months ago
- Sparse probing paper full code.☆58Updated last year
- An Open Source Implementation of Anthropic's Paper: "Towards Monosemanticity: Decomposing Language Models with Dictionary Learning"☆44Updated last year
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆233Updated last week
- ☆213Updated last year
- Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization☆26Updated 10 months ago
- ☆120Updated 10 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆95Updated 2 weeks ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆60Updated 6 months ago
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆78Updated last year
- ☆121Updated last year
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆98Updated 4 months ago
- ☆95Updated last year
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆81Updated last year