Alternatives and similar repositories for activation-steering:

Users that are interested in activation-steering are comparing it to the libraries listed below

• paul-rottger / xstest
  Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
  ☆82Updated this week
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆122Updated 8 months ago
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆62Updated 3 months ago
• yuzhaouoe / SAE-based-representation-engineering
  [NAACL'25] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering
  ☆44Updated 2 months ago
• ejones313 / auditing-llms
  ☆52Updated last year
• chrisliu298 / awesome-representation-engineering
  A resource repository for representation engineering in large language models
  ☆99Updated 3 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆87Updated last year
• logix-project / logix
  AI Logging for Interpretability and Explainability🔬
  ☆102Updated 8 months ago
• saprmarks / geometry-of-truth
  ☆76Updated 6 months ago
• fc2869 / lo-fit
  LoFiT: Localized Fine-tuning on LLM Representations
  ☆32Updated last month
• peterljq / Parsimonious-Concept-Engineering
  Implementation of PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)
  ☆32Updated 3 months ago
• dannyallover / overthinking_the_truth
  ☆30Updated 9 months ago
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆62Updated last year
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆53Updated 2 months ago
• Unispac / shallow-vs-deep-alignment
  Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep
  ☆70Updated 7 months ago
• XuandongZhao / weak-to-strong
  Weak-to-Strong Jailbreaking on Large Language Models
  ☆72Updated 11 months ago
• epfl-dlab / llm-latent-language
  Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".
  ☆65Updated 11 months ago
• Zhang-Yihao / Adversarial-Representation-Engineering
  Official implementation repository for the paper Towards General Conceptual Model Editing via Adversarial Representation Engineering.
  ☆17Updated 2 months ago
• boyiwei / alignment-attribution-code
  [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
  ☆68Updated 4 months ago
• DLR-SC / style-vectors-for-steering-llms
  Code release for the paper "Style Vectors for Steering Generative Large Language Models", accepted to the Findings of the EACL 2024.
  ☆26Updated 4 months ago
• edenbiran / HoppingTooLate
  Exploring the Limitations of Large Language Models on Multi-Hop Queries
  ☆21Updated 7 months ago
• Thartvigsen / GRACE
  [NeurIPS'23] Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
  ☆71Updated last month
• milesaturpin / cot-unfaithfulness
  ☆36Updated last year
• alisawuffles / proxy-tuning
  Code associated with Tuning Language Models by Proxy (Liu et al., 2024)
  ☆103Updated 10 months ago
• SafeAILab / RAIN
  [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning
  ☆88Updated 8 months ago
• CaoYuanpu / BiPO
  Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
  ☆17Updated 6 months ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆181Updated 4 months ago
• ykwon0407 / DataInf
  DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)
  ☆62Updated 4 months ago
• OpenMOSS / Language-Model-SAEs
  For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.
  ☆91Updated this week