Open Source Replication of Anthropic's Alignment Faking Paper
☆61Apr 4, 2025Updated last year
Alternatives and similar repositories for open-source-alignment-faking
Users that are interested in open-source-alignment-faking are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Inference API for many LLMs and other useful tools for empirical research☆143May 29, 2026Updated 5 months ago
- ☆34Nov 11, 2025Updated 11 months ago
- ☆30Jan 7, 2026Updated 10 months ago
- ☆26Jun 22, 2025Updated last year
- Auditing agents for fine-tuning safety☆22Oct 21, 2025Updated last year
- 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.
- Code for Preventing Language Models From Hiding Their Reasoning, which evaluates defenses against LLM steganography.☆25Oct 6, 2026Updated last month
- ☆16Oct 13, 2025Updated last year
- Framework for generating behavioral evaluations of frontier AI models.☆48Oct 28, 2026Updated last week
- ☆13Apr 5, 2026Updated 7 months ago
- Repository for the "Chain-of-Thought Reasoning In The Wild Is Not Always Faithful" paper☆36Mar 31, 2026Updated 7 months ago
- ☆665Jun 19, 2025Updated last year
- ☆29Oct 6, 2024Updated 2 years ago
- Accompanying codebase for neuroscope.io, a website for displaying max activating dataset examples for language model neurons☆15Feb 13, 2023Updated 3 years ago
- ☆17Jun 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.
- [ICLR 2025] On Evluating the Durability of Safegurads for Open-Weight LLMs☆13Jun 20, 2025Updated last year
- ☆51Sep 29, 2024Updated 2 years ago
- ☆35Oct 8, 2026Updated 3 weeks ago
- Code for "Unifying Grokking and Double Descent" from the NeurIPS 2022 ML Safety Workshop.☆11Feb 17, 2023Updated 3 years ago
- A research workbench for developing and testing attacks against large language models, with a focus on prompt injection vulnerabilities a…☆63Jul 24, 2026Updated 3 months ago
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆71Jun 9, 2025Updated last year
- ☆25Feb 17, 2026Updated 8 months ago
- Training Transformers with knowledge localization (SGTM)☆57Jan 11, 2026Updated 9 months ago
- Ember is a hosted API/SDK that lets you shape AI model behavior by directly controlling a model's internal units of computation, or "feat…☆55Jul 14, 2025Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆22Sep 9, 2021Updated 5 years ago
- gpt completions in vscode☆35Mar 24, 2023Updated 3 years ago
- Prompts used in the Automated Auditing Blog Post☆172Jul 24, 2025Updated last year
- Have an LLM write your biography, probably incorrectly☆15Dec 26, 2024Updated last year
- Official Repository of Surprising Anecdotes for AI Finds a Way☆15Aug 27, 2026Updated 2 months ago
- Improving Alignment and Robustness with Circuit Breakers☆271Sep 24, 2024Updated 2 years ago
- ☆20Updated this week
- ☆22Nov 15, 2024Updated last year
- 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
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- ☆43May 21, 2025Updated last year
- ☆14Dec 4, 2024Updated last year
- ☆11Mar 6, 2022Updated 4 years ago
- Code for the paper: Linear Control of Test Awareness Reveals Differential Compliance in Reasoning Models☆15Jul 2, 2026Updated 4 months ago
- ☆164Feb 10, 2026Updated 8 months ago
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.☆265Oct 26, 2026Updated last week
- Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"☆22Sep 21, 2025Updated last year