© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 53717
    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
    Negative Logits
    à¸Ńà¸ĩà¸Īาà¸ģ
    -0.07
    aldi
    -0.07
    onda
    -0.07
    chter
    -0.07
    avn
    -0.07
    elsing
    -0.07
    istol
    -0.07
    "$
    -0.07
    printStats
    -0.07
    onde
    -0.07
    POSITIVE LOGITS
    bbe
    0.07
     Caldwell
    0.06
     himself
    0.06
     ASIC
    0.06
     Everyone
    0.05
     everyone
    0.05
    es
    0.05
     Austral
    0.05
    TERS
    0.05
    -navbar
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.