© 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. 15-LLAMASCOPE-RES-131K
    11. 87772
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     beep
    -0.06
    ssel
    -0.06
     seins
    -0.06
    irts
    -0.06
    uler
    -0.06
    acman
    -0.06
    oreach
    -0.06
    lickr
    -0.06
     often
    -0.06
    inis
    -0.06
    POSITIVE LOGITS
    axon
    0.07
     ydk
    0.07
    TypeDef
    0.07
    ìķ¤
    0.07
    geist
    0.07
     ìĤ¬ìĭ¤
    0.07
    ugi
    0.06
    REFERRED
    0.06
    à¹Īาà¸Īะ
    0.06
     æĿ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.