© 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. 72133
    Prev
    Next
    INDEX
    Explanations

    JavaScript function declarations and DOM manipulation commands

    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
    hausen
    -0.07
    ET
    -0.06
    /rfc
    -0.06
     Alley
    -0.06
    ensen
    -0.06
    owned
    -0.06
    amarin
    -0.06
    arga
    -0.06
    _##
    -0.06
    aram
    -0.06
    POSITIVE LOGITS
    acro
    0.06
     Berk
    0.06
    ÑŁ
    0.06
    adık
    0.06
    ediÄŁi
    0.06
    £i
    0.06
    ivar
    0.06
    ieber
    0.06
    .toolbox
    0.06
    364
    0.06
    Activations Density 0.006%

    No Known Activations