Extract residual-stream activations and apply steering vectors (including activation oracles) to any vLLM model during inference.
☆121Aug 11, 2026Updated last week
Alternatives and similar repositories for vllm-lens
Users that are interested in vllm-lens are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Repo for vLLM Hook, an vLLM plug-in for programming internal states of models deployed on vLLM☆154Updated this week
- Unified access to Large Language Model modules using NNsight☆119Jul 28, 2026Updated 3 weeks ago
- A toolkit that provides a range of model diffing techniques including a UI to visualize them interactively.☆80Jul 20, 2026Updated last month
- This was designed for interp researchers who want to do research on or with interp agents to give quality of life improvements and fix …☆146Feb 8, 2026Updated 6 months ago
- Engine for collecting, uploading, and downloading model activations☆31Apr 2, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- James' cookbook of evaluations and finetuning experiments☆34Feb 19, 2026Updated 6 months ago
- Tools for optimizing steering vectors in LLMs.☆22Apr 10, 2025Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆1,045Updated this week
- Linear Relational Embeddings (LREs) and Linear Relational Concepts (LRCs) for LLMs in PyTorch☆11Aug 7, 2024Updated 2 years ago
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.☆225Updated this week
- A python library built on top of UKAISI Inspect to support Control research, by Redwood☆30Updated this week
- Code for Negation Neglect☆16May 22, 2026Updated 3 months ago
- Applying SAEs for fine-grained control☆27Dec 15, 2024Updated last year
- ☆39May 7, 2026Updated 3 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆18Jul 9, 2025Updated last year
- Course Materials for Interpretability of Large Language Models (0368.4264) at Tel Aviv University☆337Feb 8, 2026Updated 6 months ago
- Agent observability and replay tooling for AI safety & interpretability research.☆113Jun 19, 2026Updated 2 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆68Oct 27, 2024Updated last year
- ☆86Feb 25, 2025Updated last year
- Repository for "Training Language Models To Explain Their Own Computations"☆35Jul 7, 2026Updated last month
- The open-source AISI toolkit for sandboxing agentic evaluations☆28Aug 7, 2025Updated last year
- The Assistant Axis is a direction in activation space that captures how "Assistant-like" a model's behavior is. Models can drift away fro…☆166Jan 20, 2026Updated 7 months ago
- A Unified Framework for High-Performance and Extensible LLM Steering☆293Aug 6, 2026Updated 2 weeks ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆20Apr 10, 2025Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Jan 19, 2025Updated last year
- Official codebase for "Analyzing the Generalization and Reliability of Steering Vectors"☆22Dec 14, 2024Updated last year
- In-depth analysis of AI agent transcripts.☆61Updated this week
- Collection of evals for Inspect AI☆639Updated this week
- Training Sparse Autoencoders on Language Models☆1,509Aug 10, 2026Updated last week
- ☆17May 19, 2026Updated 3 months ago
- Official implementation of "Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought" (NeurIPS 2025)☆44Oct 8, 2025Updated 10 months ago
- Code repo for the model organisms and convergent directions of EM papers.☆81Sep 22, 2025Updated 11 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆122Updated this week
- ☆57Jul 4, 2025Updated last year
- Open Character Training☆96Apr 4, 2026Updated 4 months ago
- A library for mechanistic interpretability of GPT-style language models☆3,813Updated this week
- ☆428Aug 21, 2025Updated last year
- Code for the "Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning" paper.☆18Jul 6, 2026Updated last month
- Mechanistic Interpretability Visualizations using React☆367Apr 30, 2026Updated 3 months ago