Skip to content

@TransluceAI Transluce

Change the repository type filter

All

    Repositories list

    8 repositories

    • introspective-interp

      Public
      Repository for "Training Language Models To Explain Their Own Computations"
      Python
      •
      MIT License
      •3•15•1•1•Updated Dec 22, 2025Dec 22, 2025

    • docent

      Public
      Python
      •
      Other
      •7•77•0•0•Updated Dec 18, 2025Dec 18, 2025

    • .github

      Public
      1•18•0•0•Updated Dec 12, 2025Dec 12, 2025

    • observatory

      Public
      A toolkit for describing model features and intervening on those features to steer behavior.
      Python
      •
      MIT License
      •20•225•4•3•Updated Dec 12, 2025Dec 12, 2025

    • tau2-bench

      Public
      τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment
      Python
      •
      MIT License
      •136•0•0•0•Updated Sep 16, 2025Sep 16, 2025

    • jailbreaking-frontier-models

      Public
      Python
      •4•21•0•0•Updated Sep 3, 2025Sep 3, 2025

    • inspect_ai

      Public
      Inspect: A framework for large language model evaluations
      Python
      •
      MIT License
      •365•6•0•0•Updated Mar 25, 2025Mar 25, 2025

    • inspect_evals

      Public archive
      Collection of evals for Inspect AI
      Python
      •
      MIT License
      •220•1•0•0•Updated Jan 29, 2025Jan 29, 2025