© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 81316
    Prev
    Next
    INDEX
    Explanations

    references to accountability and reporting structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    argent
    -0.07
    iele
    -0.07
    endale
    -0.07
    ppo
    -0.07
     gec
    -0.07
    _drv
    -0.07
    οÏħÏĤ
    -0.07
    úi
    -0.07
    nock
    -0.07
    iox
    -0.07
    POSITIVE LOGITS
     final
    0.08
     hopes
    0.07
     plan
    0.07
     hope
    0.07
     also
    0.07
     plans
    0.07
     future
    0.07
     ca
    0.07
     sill
    0.07
     conclusion
    0.06
    Activations Density 0.015%

    No Known Activations