chrisliu298 / awesome-representation-engineeringLinks
A resource repository for representation engineering in large language models
☆136Updated 10 months ago
Alternatives and similar repositories for awesome-representation-engineering
Users that are interested in awesome-representation-engineering are comparing it to the libraries listed below
Sorting:
- [ICLR 2025] General-purpose activation steering library☆107Updated 2 weeks ago
- Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization☆30Updated last year
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆80Updated 6 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆115Updated 7 months ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆84Updated 6 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆97Updated 2 years ago
- Steering Llama 2 with Contrastive Activation Addition☆182Updated last year
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)☆77Updated last year
- awesome SAE papers☆45Updated 4 months ago
- A curated list of resources for activation engineering☆102Updated 4 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆87Updated last year
- LLM Unlearning☆175Updated last year
- ☆230Updated last year
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆153Updated 5 months ago
- ☆61Updated last year
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆63Updated 10 months ago
- ☆63Updated 7 months ago
- ☆174Updated 10 months ago
- This is the official code for the paper "Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable".☆25Updated 6 months ago
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆61Updated 3 months ago
- ☆177Updated last year
- A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..☆271Updated 6 months ago
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆96Updated 4 months ago
- ☆51Updated 2 months ago
- ☆56Updated 2 years ago
- Toolkit for evaluating the trustworthiness of generative foundation models.☆118Updated last month
- Using sparse coding to find distributed representations used by neural networks.☆272Updated last year
- ☆41Updated last year
- Function Vectors in Large Language Models (ICLR 2024)☆180Updated 5 months ago
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆89Updated last year