☆37Oct 8, 2026Updated last month
Alternatives and similar repositories for auditing-agents
Users that are interested in auditing-agents are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆15Dec 4, 2024Updated last year
- Reproducing "Natural Emergent Misalignment from Reward Hacking" (MacDiarmid et al., Anthropic 2025) with open-source models. Includes rew…☆36Oct 5, 2026Updated last month
- Codebase for Distillation Robustifies Unlearning☆11Jun 11, 2025Updated last year
- ☆67Jul 4, 2025Updated last year
- Prompts used in the Automated Auditing Blog Post☆172Jul 24, 2025Updated last year
- 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.
- Integration between Inspect and Weights & Biases☆24Oct 24, 2026Updated 3 weeks ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆34May 23, 2024Updated 2 years ago
- A library for activation patching based on nnsight.☆12May 27, 2025Updated last year
- ☆21Mar 16, 2026Updated 7 months ago
- Teach LLMs to use NNSight with Skills☆15Updated this week
- ☆13Sep 11, 2025Updated last year
- ☆47Feb 18, 2026Updated 8 months ago
- A suite of interpretability tasks to evaluate agents using Scribe for notebook access☆18Oct 2, 2025Updated last year
- ☆22Dec 29, 2025Updated 10 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Code and data for NAACL 2025 paper "IHEval: Evaluating Language Models on Following the Instruction Hierarchy"☆19Feb 25, 2025Updated last year
- Code for the "Mechanisms of Introspective Awareness" paper.☆48Apr 16, 2026Updated 6 months ago
- ☆16Oct 13, 2025Updated last year
- Running UK AISI's Inspect in the Cloud☆25May 6, 2026Updated 6 months ago
- Open Source Replication of Anthropic's Alignment Faking Paper☆62Apr 4, 2025Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆21Jan 19, 2025Updated last year
- A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents☆14Nov 8, 2026Updated last week
- ☆37Jun 4, 2025Updated last year
- Open problems, research agendas, and papers in Math for AI Safety — public from draft stage onward☆78Oct 6, 2026Updated last month
- 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.
- A unified API gateway for multiple LLM providers with OpenAI-compatible endpoints☆13Updated this week
- ☆12Dec 24, 2025Updated 10 months ago
- A toolkit that provides a range of model diffing techniques including a UI to visualize them interactively.☆89Oct 25, 2026Updated 2 weeks ago
- ☆21Aug 17, 2026Updated 2 months ago
- Open Character Training☆107Apr 4, 2026Updated 7 months ago
- Trains small LMs. Designed for training on SimpleStories☆17Aug 6, 2026Updated 3 months ago
- ☆17May 21, 2026Updated 5 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 9 months ago
- ☆27Mar 30, 2026Updated 7 months ago
- 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.
- ☆14Oct 6, 2026Updated last month
- Trail is an Obsidian plugin enabling strong typed relations between files☆12Feb 20, 2026Updated 8 months ago
- ☆16May 15, 2026Updated 5 months ago
- Interpretability faithfulness and introspection in conversational LLMs☆14May 29, 2024Updated 2 years ago
- Mapping out the "memory" of neural nets with data attribution☆110Updated this week
- ☆23Apr 28, 2026Updated 6 months ago
- ☆34Nov 11, 2025Updated last year
Are these results useful?