© 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. 15-LLAMASCOPE-RES-131K
    11. 88796
    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
    uyo
    -0.06
     trif
    -0.06
     satisf
    -0.06
    гал
    -0.05
    oter
    -0.05
    ót
    -0.05
    istrar
    -0.05
    zer
    -0.05
     Parsons
    -0.05
     BASE
    -0.05
    POSITIVE LOGITS
    represent
    0.07
     representatives
    0.07
     ç©
    0.07
    ritz
    0.07
    eting
    0.06
    /forum
    0.06
    quete
    0.06
    resco
    0.06
    èĭ±æĸĩ
    0.06
     hrs
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.