Alternatives and similar repositories for activation-steering:

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

• yuzhaouoe / SAE-based-representation-engineering
  [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering
  ☆54Updated 5 months ago
• paul-rottger / xstest
  Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
  ☆95Updated 2 months ago
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆72Updated last month
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆147Updated 11 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆91Updated last year
• chrisliu298 / awesome-representation-engineering
  A resource repository for representation engineering in large language models
  ☆121Updated 5 months ago
• epfl-dlab / llm-latent-language
  Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".
  ☆73Updated last year
• javiferran / sae_entities
  ☆29Updated last month
• fc2869 / lo-fit
  LoFiT: Localized Fine-tuning on LLM Representations
  ☆37Updated 3 months ago
• DAMO-NLP-SG / multilingual_analysis
  [NeurIPS 2024] How do Large Language Models Handle Multilingualism?
  ☆32Updated 5 months ago
• roeehendel / icl_task_vectors
  ☆93Updated last year
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆64Updated last year
• balevinstein / Probes
  ☆50Updated last year
• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆46Updated 7 months ago
• boyiwei / alignment-attribution-code
  [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
  ☆76Updated last month
• vinid / safety-tuned-llamas
  ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.
  ☆82Updated 11 months ago
• ejones313 / auditing-llms
  ☆54Updated 2 years ago
• milesaturpin / cot-unfaithfulness
  ☆42Updated last year
• MaheepChaudhary / SAE-Ravel
  Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…
  ☆11Updated 3 months ago
• eric-mitchell / serac
  Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model
  ☆68Updated 2 years ago
• yihuaihong / ConceptVectors
  ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"
  ☆35Updated 2 months ago
• CaoYuanpu / BiPO
  Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
  ☆22Updated 9 months ago
• dannyallover / overthinking_the_truth
  ☆29Updated last year
• ykwon0407 / DataInf
  DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)
  ☆64Updated 7 months ago
• swj0419 / muse_bench
  ☆21Updated last month
• rishub-tamirisa / tamper-resistance
  [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"
  ☆54Updated 2 months ago
• SafeAILab / RAIN
  [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning
  ☆92Updated 11 months ago
• SALT-NLP / chain-of-thought-bias
  ☆25Updated 7 months ago
• Thartvigsen / GRACE
  [NeurIPS'23] Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
  ☆75Updated 4 months ago
• OpenMOSS / Language-Model-SAEs
  For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.
  ☆113Updated this week