© 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. 9-LLAMASCOPE-RES-131K
    11. 99011
    Prev
    Next
    INDEX
    Explanations

    references to the score and performance in sports games

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    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
    åħį
    -0.07
    hardt
    -0.07
    .cgi
    -0.06
    ouv
    -0.06
    ÑĢек
    -0.06
    -в
    -0.06
    attendance
    -0.06
    ittings
    -0.06
    iddy
    -0.06
     Dans
    -0.06
    POSITIVE LOGITS
    ypy
    0.07
     seals
    0.06
    ÑĥÑĢг
    0.06
    369
    0.06
     Seal
    0.06
    843
    0.06
     Cinema
    0.06
     bench
    0.06
    acer
    0.06
    fü
    0.06
    Activations Density 0.007%

    No Known Activations