© 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. 40489
    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
     tez
    -0.06
    tual
    -0.06
    xcd
    -0.06
     Maiden
    -0.06
    ull
    -0.06
    alık
    -0.06
    oner
    -0.06
    ials
    -0.06
     “
    -0.06
    ones
    -0.06
    POSITIVE LOGITS
    inet
    0.07
    вÑĸÑĤ
    0.07
    bbie
    0.06
    ÑĥÑĢа
    0.06
     <!
    0.06
    agon
    0.06
    Question
    0.06
    buah
    0.06
    prev
    0.06
    átis
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.