© 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. 54030
    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
    æķ
    -0.07
    andon
    -0.07
    anko
    -0.06
    weeted
    -0.06
    yte
    -0.06
    py
    -0.06
    otos
    -0.06
    ¼åIJĪ
    -0.06
    ropri
    -0.06
    enses
    -0.06
    POSITIVE LOGITS
    arkan
    0.07
    auc
    0.06
    ãĥ¼ãĥŀ
    0.06
    erece
    0.06
    arme
    0.06
    icia
    0.06
    bjerg
    0.06
    ãģıãĤĮ
    0.06
    gow
    0.06
     -------------------------------------------------------------------------
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.