© 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. 18668
    Prev
    Next
    INDEX
    Explanations

    variables and values used in coding or programming contexts

    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
    bsd
    -0.07
    à¸Ńà¸ģ
    -0.07
    à¸İ
    -0.07
    strcasecmp
    -0.06
    adro
    -0.06
    imentos
    -0.06
    alse
    -0.06
    dera
    -0.06
    _errno
    -0.06
    .pat
    -0.06
    POSITIVE LOGITS
     =
    0.09
    éļĽ
    0.06
    ãĥĥ
    0.06
    istrovstvÃŃ
    0.06
    ##_
    0.06
    tempts
    0.06
    hei
    0.06
    inerary
    0.06
     rit
    0.06
    -editor
    0.06
    Activations Density 0.023%

    No Known Activations