© 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. 91867
    Prev
    Next
    INDEX
    Explanations

    HTML and JavaScript code structures

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     laser
    -0.06
    ÑģÑıÑĤ
    -0.06
    ensed
    -0.06
    ç´§
    -0.06
     Middleware
    -0.06
    à¸łà¸²à¸ŀ
    -0.06
     Laser
    -0.06
     <!--[
    -0.06
     Rounds
    -0.05
    ythe
    -0.05
    POSITIVE LOGITS
    DRV
    0.07
    emez
    0.07
    SHARE
    0.07
    ptal
    0.07
    /button
    0.07
    getWidth
    0.07
    uzey
    0.07
     dress
    0.07
    ityEngine
    0.07
    /******/
    0.07
    Activations Density 0.013%

    No Known Activations