© 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. 14214
    Prev
    Next
    INDEX
    Explanations

    programming-related technical elements and syntax

    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
    ubber
    -0.07
    cÃŃ
    -0.07
     prospect
    -0.07
    ilip
    -0.07
     substance
    -0.07
    _hub
    -0.06
     Substance
    -0.06
    udad
    -0.06
    .Rad
    -0.06
    overlap
    -0.06
    POSITIVE LOGITS
     yyn
    0.07
    .row
    0.06
    :indexPath
    0.06
    avin
    0.06
     '\''
    0.06
    ÑĤÑĥ
    0.06
    483
    0.06
    NSIndexPath
    0.06
     NSIndexPath
    0.06
    conde
    0.06
    Activations Density 0.000%

    No Known Activations