GraySwanAI / circuit-breakers
Improving Alignment and Robustness with Circuit Breakers
☆176Updated 4 months ago
Alternatives and similar repositories for circuit-breakers:
Users that are interested in circuit-breakers are comparing it to the libraries listed below
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆163Updated 3 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆84Updated last year
- Röttger et al. (2023): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆79Updated last year
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆95Updated 9 months ago
- Steering Llama 2 with Contrastive Activation Addition☆119Updated 8 months ago
- ☆139Updated this week
- Steering vectors for transformer language models in Pytorch / Huggingface☆81Updated 2 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆135Updated 3 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆113Updated 6 months ago
- A resource repository for representation engineering in large language models☆98Updated 2 months ago
- Weak-to-Strong Jailbreaking on Large Language Models☆72Updated 11 months ago
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆110Updated 7 months ago
- ☆135Updated this week
- Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs☆57Updated last month
- ☆161Updated last year
- We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20…☆266Updated 11 months ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆87Updated this week
- [NeurIPS 2024] Knowledge Circuits in Pretrained Transformers☆120Updated last month
- General-purpose activation steering library☆42Updated 3 weeks ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆26Updated 8 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆88Updated 8 months ago
- [ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use☆125Updated 10 months ago
- ☆187Updated 11 months ago
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆44Updated last week
- ☆202Updated 3 months ago
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆66Updated 11 months ago
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆88Updated 10 months ago
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆82Updated 8 months ago
- AI Logging for Interpretability and Explainability🔬☆100Updated 7 months ago
- Algebraic value editing in pretrained language models☆62Updated last year