[ICLR 2025] General-purpose activation steering library
☆150Sep 18, 2025Updated 6 months ago
Alternatives and similar repositories for activation-steering
Users that are interested in activation-steering are comparing it to the libraries listed below
Sorting:
- A resource repository for representation engineering in large language models☆149Nov 14, 2024Updated last year
- ☆16Sep 1, 2025Updated 6 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆27Nov 20, 2024Updated last year
- Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization☆43Jul 28, 2024Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆214May 23, 2024Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆175Mar 12, 2026Updated last week
- Steering vectors for transformer language models in Pytorch / Huggingface☆140Feb 21, 2025Updated last year
- 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…☆13Jan 26, 2025Updated last year
- Code to enable layer-level steering in LLMs using sparse auto encoders☆31Sep 18, 2025Updated 6 months ago
- ☆30Aug 2, 2024Updated last year
- Materials for "Multi-property Steering of Large Language Models with Dynamic Activation Composition"☆14Nov 22, 2024Updated last year
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆20Oct 18, 2024Updated last year
- Algebraic value editing in pretrained language models☆69Nov 1, 2023Updated 2 years ago
- ☆41May 9, 2025Updated 10 months ago
- Code for In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering☆198Feb 13, 2025Updated last year
- Localization of Knowledge in Text-to-Image Models☆12Oct 8, 2024Updated last year
- Accepted by IJCAI-24 Survey Track☆230Aug 25, 2024Updated last year
- Official codebase for "Analyzing the Generalization and Reliability of Steering Vectors"☆20Dec 14, 2024Updated last year
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆361Jun 13, 2025Updated 9 months ago
- [ICLR 2026] The implementation of paper "AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint"☆43Nov 20, 2025Updated 4 months ago
- ☆210Oct 14, 2025Updated 5 months ago
- Repository for the Paper: Refusing Safe Prompts for Multi-modal Large Language Models☆18Oct 16, 2024Updated last year
- Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…☆272Jan 10, 2026Updated 2 months ago
- Code release for the paper "Style Vectors for Steering Generative Large Language Models", accepted to the Findings of the EACL 2024.☆36Sep 26, 2024Updated last year
- ☆28Nov 28, 2024Updated last year
- ☆29Nov 16, 2025Updated 4 months ago
- Modified to support crosscoder training.☆25Feb 4, 2026Updated last month
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆868Mar 6, 2026Updated 2 weeks ago
- QRHead: Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking☆38Jan 20, 2026Updated 2 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆63Oct 27, 2024Updated last year
- ☆18Jan 17, 2024Updated 2 years ago
- A curated list of resources for activation engineering☆132Oct 2, 2025Updated 5 months ago
- Code for Representation Bending Paper☆17Jul 15, 2025Updated 8 months ago
- Applying SAEs for fine-grained control☆26Dec 15, 2024Updated last year
- A library for mechanistic interpretability of GPT-style language models☆3,183Mar 13, 2026Updated last week
- open-source code for paper: Retrieval Head Mechanistically Explains Long-Context Factuality☆236Aug 2, 2024Updated last year
- Code for Reducing Hallucinations in Vision-Language Models via Latent Space Steering☆105Nov 23, 2024Updated last year
- ☆251Feb 22, 2024Updated 2 years ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆863Updated this week