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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 87727
    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
    yd
    -0.08
     Ridley
    -0.07
    chwitz
    -0.07
     pok
    -0.07
    hei
    -0.07
     Berk
    -0.06
    ripp
    -0.06
    logg
    -0.06
     Breed
    -0.06
    asio
    -0.06
    POSITIVE LOGITS
    éºĹ
    0.07
    664
    0.06
    utm
    0.06
    ÐIJÑĢÑħÑĸв
    0.06
    ãģijãĤĮãģ©
    0.06
    .volley
    0.06
    $__
    0.06
    calloc
    0.06
    unset
    0.06
    VarChar
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.