© 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. 41587
    Prev
    Next
    INDEX
    Explanations

    references to musical performance and participation in bands

    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
    twig
    -0.08
    /Branch
    -0.08
    eview
    -0.08
     Incontri
    -0.08
    umbo
    -0.07
    TargetException
    -0.07
     гол
    -0.07
    à¥įà¤
    -0.07
    tryside
    -0.07
     fkk
    -0.07
    POSITIVE LOGITS
     band
    0.10
     bands
    0.09
    band
    0.09
     local
    0.09
    bands
    0.09
    -band
    0.07
     pit
    0.07
     Band
    0.07
    local
    0.07
     pits
    0.07
    Activations Density 0.029%

    No Known Activations