© 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 EvalsExportsAPI 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. 87423
    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
    ÑĢаб
    -0.08
    анка
    -0.06
     helicopt
    -0.06
    žÃŃ
    -0.06
     Fog
    -0.06
     desar
    -0.06
     Kushner
    -0.06
    utton
    -0.06
    oins
    -0.06
     stir
    -0.06
    POSITIVE LOGITS
     grav
    0.07
    .handlers
    0.07
    Łèĥ½
    0.07
    -toggler
    0.06
     gray
    0.06
    -www
    0.06
    indre
    0.06
    onder
    0.06
    iyan
    0.06
    èĩ´
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.