The Assistant Axis is a direction in activation space that captures how "Assistant-like" a model's behavior is. Models can drift away from the Assistant during conversations—sometimes toward bizarre or harmful personas. This repo contains a pipeline for generating the Assistant Axis and notebooks for monitoring and steering with it.
☆158Jan 20, 2026Updated 6 months ago
Alternatives and similar repositories for assistant-axis
Users that are interested in assistant-axis are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models☆452Apr 22, 2026Updated 3 months ago
- ☆95Apr 18, 2026Updated 3 months ago
- Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""☆20Oct 11, 2024Updated last year
- Repository for "Training Language Models To Explain Their Own Computations"☆23Jul 7, 2026Updated 2 weeks ago
- Inference API for many LLMs and other useful tools for empirical research☆134May 29, 2026Updated last month
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Training LLMs to Report Their Learned Behaviors☆27Apr 28, 2026Updated 2 months ago
- Extract residual-stream activations and apply steering vectors (including activation oracles) to any vLLM model during inference.☆117Updated this week
- Code repo for the model organisms and convergent directions of EM papers.☆72Sep 22, 2025Updated 10 months ago
- 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 5 months ago
- ☆50Jul 4, 2025Updated last year
- ☆21Mar 3, 2026Updated 4 months ago
- bloom - evaluate any behavior immediately 🌸🌱☆1,371May 7, 2026Updated 2 months ago
- A toolkit that provides a range of model diffing techniques including a UI to visualize them interactively.☆78Updated this week
- Unified access to Large Language Model modules using NNsight☆116Jul 2, 2026Updated 3 weeks ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆314Jan 12, 2026Updated 6 months ago
- Repo for measuring whether using AI tools inhibits skill formation and development☆15Jan 3, 2026Updated 6 months ago
- ☆25Mar 30, 2026Updated 3 months ago
- ☆16Nov 14, 2025Updated 8 months ago
- [COLM 2026] Official implementation for "MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Mo…☆20Apr 23, 2026Updated 3 months ago
- Code for Negation Neglect☆16May 22, 2026Updated 2 months ago
- A library for training crosscoders☆17May 28, 2025Updated last year
- Open-sourced evaluation suite from the Monitoring Monitorability paper☆88Jun 11, 2026Updated last month
- An alignment auditing agent capable of quickly exploring alignment hypothesis☆1,270Updated this week
- 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.
- Parameter Decomposition☆134Updated this week
- MishformerLens intends to be a drop-in replacement for TransformerLens that AST patches HuggingFace Transformers rather than implementing…☆10Oct 7, 2024Updated last year
- A Node.Js / Neo4J tool that translates words and relations into network graphs and shows you how it all connects.☆13Oct 24, 2019Updated 6 years ago
- Datasets used in the paper "Reward hacking behavior can generalize across tasks"☆15Aug 17, 2025Updated 11 months ago
- ⚓️ Repository for the "Thought Anchors: Which LLM Reasoning Steps Matter?" paper.☆137Oct 27, 2025Updated 8 months ago
- ☆2,874Jul 18, 2026Updated last week
- open source interpretability platform 🧠☆1,081Jul 17, 2026Updated last week
- Training Sparse Autoencoders on Language Models☆1,484Updated this week
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆210Mar 12, 2026Updated 4 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- ☆114Aug 8, 2024Updated last year
- Code to generate figures of paper "When do spectral gradient updates help in deep learning?"☆16Dec 3, 2025Updated 7 months ago
- ☆152Feb 10, 2026Updated 5 months ago
- ☆1,187Updated this week
- ☆86Feb 25, 2025Updated last year
- An interpretable kNN based on aggregating the predictions of multiple 2d spaces.☆13Oct 21, 2024Updated last year
- [ICLR 2025] General-purpose activation steering library☆181Sep 18, 2025Updated 10 months ago