Code repository for "Eliciting Secret Knowledge from Language Models"
☆24Nov 3, 2026Updated 2 weeks ago
Alternatives and similar repositories for eliciting-secret-knowledge
Users that are interested in eliciting-secret-knowledge are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A toolkit that provides a range of model diffing techniques including a UI to visualize them interactively.☆90Oct 25, 2026Updated 3 weeks ago
- ☆27Mar 30, 2026Updated 7 months ago
- Code for the "Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning" paper.☆20Jul 6, 2026Updated 4 months ago
- Code for the "Mechanisms of Introspective Awareness" paper.☆49Apr 16, 2026Updated 7 months ago
- ☆12Nov 11, 2025Updated last year
- 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.
- 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
- Applying SAEs for fine-grained control☆28Dec 15, 2024Updated last year
- [ICLR 2025 Oral] Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition☆17Nov 25, 2024Updated last year
- Inference API for many LLMs and other useful tools for empirical research☆143May 29, 2026Updated 5 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆159Sep 14, 2022Updated 4 years ago
- ☆225Oct 14, 2025Updated last year
- ☆13Sep 11, 2025Updated last year
- No-chain-of-thought reasoning benchmark (NCRI): sealed banks, no-CoT runner with witnesses, frozen placement, scores for 285 models☆29Nov 9, 2026Updated last week
- ☆41May 7, 2026Updated 6 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.
- ☆15Dec 4, 2024Updated last year
- Codebase for paper: "Counterfactual Simulation Training for Chain-of-Thought Faithfulness"☆19Jun 18, 2026Updated 5 months ago
- Unified access to Large Language Model modules using NNsight☆124Updated this week
- Benchmark dataset for evaluating trusted monitors on AI agent transcripts☆21May 16, 2026Updated 6 months ago
- A replication of "Toy Models of Superposition," a groundbreaking machine learning research paper published by authors affiliated with Ant…☆11Dec 30, 2023Updated 2 years ago
- ☆10Oct 27, 2020Updated 6 years ago
- Code and data for editing model beliefs with SDF and other methods, and for evaluating the depth of the implanted beliefs.☆20Oct 23, 2025Updated last year
- ☆20Jun 3, 2026Updated 5 months ago
- ☆13Dec 20, 2019Updated 6 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ⚓️ Repository for the "Thought Anchors: Which LLM Reasoning Steps Matter?" paper.☆147Oct 27, 2025Updated last year
- Code repo for the model organisms and convergent directions of EM papers.☆90Sep 22, 2025Updated last year
- [COLING 2025] Let's Focus on Neuron: Neuron-Level Supervised Fine-tuning for Large Language Model☆10Jan 17, 2025Updated last year
- ☆90Feb 18, 2026Updated 9 months ago
- 2019 PyCon kr tutorial: "네이버 영화 평점 데이터로 자연어처리 논문 구현 시작하기"☆13Aug 21, 2019Updated 7 years ago
- Theorems, not tests: kernel-checked guarantees for Pythia-14M and a neural PDE solver, in Lean 4☆24Updated this week
- A cross platform console tool for racaljk/hosts.☆12Aug 28, 2016Updated 10 years ago
- ☆26Dec 20, 2023Updated 2 years ago
- ☆142Oct 28, 2023Updated 3 years 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.
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆492Jun 13, 2025Updated last year
- Data Laundering: Artificially Boosting Benchmark Results through Knowledge Distillation☆11Jan 24, 2025Updated last year
- ☆16Jul 11, 2023Updated 3 years ago
- A Complex Judge, designed for ACOJ.☆10Sep 5, 2016Updated 10 years ago
- Experiment management with Hydra and MLflow☆13Nov 20, 2020Updated 5 years ago
- Generating, validating and running exploitable verifiable coding problems☆15Sep 30, 2026Updated last month
- This is the official implementation for our ACL 2024 paper: "Causal Estimation of Memorisation Profiles".☆25Mar 25, 2025Updated last year
Are these results useful?