Open-sourced evaluation suite from the Monitoring Monitorability paper
☆102Aug 17, 2026Updated last month
Alternatives and similar repositories for monitorability-evals
Users that are interested in monitorability-evals are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICML 2026] An Evaluation Suite for Chain-of-Thought Controllability☆57Mar 10, 2026Updated 7 months ago
- https://scale.com/research/mrt☆20Mar 16, 2026Updated 6 months ago
- Applies ROME and MEMIT on Mamba-S4 models☆16Apr 5, 2024Updated 2 years ago
- ☆25Jun 30, 2025Updated last year
- ☆23Mar 11, 2026Updated 7 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Code for "On Measuring Faithfulness of Natural Language Explanations"☆23Jul 14, 2026Updated 3 months ago
- Code repo for the model organisms and convergent directions of EM papers.☆86Sep 22, 2025Updated last year
- ☆120Sep 30, 2026Updated 2 weeks ago
- Landing page for MIB: A Mechanistic Interpretability Benchmark☆27Aug 15, 2025Updated last year
- ⚓️ Repository for the "Thought Anchors: Which LLM Reasoning Steps Matter?" paper.☆144Oct 27, 2025Updated 11 months ago
- Easily deploy my zsh and tmux configuration on new machines. Includes local and remote aliases to improve workflow.☆16Apr 23, 2026Updated 5 months ago
- CyberGym-E2E is a large-scale benchmark built from real-world vulnerabilities in widely used open-source projects to evaluate AI agents' …☆84Oct 7, 2026Updated last week
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models☆466Apr 22, 2026Updated 5 months ago
- Code for evaluating AI systems on the MASK honesty benchmark.☆27Mar 6, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Syntax for searching with natural language from Lean, using https://leansearch.net/ (may extend to other services)☆37Oct 6, 2026Updated last week
- The Assistant Axis is a direction in activation space that captures how "Assistant-like" a model's behavior is. Models can drift away fro…☆178Jan 20, 2026Updated 8 months ago
- The Order of the Agents is a council of AI agents (Codex, Claude) that deliberate to produce final plans, PRDs, and decisions.☆21Apr 29, 2026Updated 5 months ago
- The Structure and Interpretation of Deep Networks Handbook☆14Dec 14, 2024Updated last year
- ☆19Apr 5, 2025Updated last year
- Training LLMs to Report Their Learned Behaviors☆30Apr 28, 2026Updated 5 months ago
- An alignment auditing agent capable of quickly exploring alignment hypothesis☆1,375Updated this week
- A suite of interpretability tasks to evaluate agents using Scribe for notebook access☆18Oct 2, 2025Updated last year
- Datasets used in the paper "Reward hacking behavior can generalize across tasks"☆16Aug 17, 2025Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- A python sdk for LLM finetuning and inference on runpod infrastructure☆30Updated this week
- Unified access to Large Language Model modules using NNsight☆121Updated this week
- The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes☆19Oct 3, 2026Updated last week
- Attribution-based Parameter Decomposition☆35Jun 11, 2025Updated last year
- ☆337Jan 12, 2026Updated 9 months ago
- ☆65Jul 4, 2025Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆1,123Updated this week
- ☆26Jul 8, 2026Updated 3 months ago
- Inference API for many LLMs and other useful tools for empirical research☆139May 29, 2026Updated 4 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Official implementation of Stackelberg PPO for morphology–control co-design.☆19Mar 17, 2026Updated 6 months ago
- Improving transparency of large language models' reasoning☆15Nov 25, 2025Updated 10 months ago
- [NeurIPS 2025 MechInterp Workshop - Spotlight] Official implementation of the paper "RelP: Faithful and Efficient Circuit Discovery in La…☆29Nov 3, 2025Updated 11 months ago
- Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""☆20Oct 11, 2024Updated 2 years ago
- ☆60Jul 29, 2026Updated 2 months ago
- 6,080-param transformer achieving 100% accuracy on 10-digit addition. Trained from scratch in 10 minutes.☆22Feb 19, 2026Updated 7 months ago
- ☆56Oct 23, 2023Updated 2 years ago