© 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. 42534
    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
    xoops
    -0.07
    ynes
    -0.06
     Burl
    -0.06
     Hubb
    -0.06
    ervo
    -0.06
    CORE
    -0.06
    뢰
    -0.06
    FRING
    -0.06
    Parms
    -0.06
    .shows
    -0.06
    POSITIVE LOGITS
    shan
    0.06
    ElementException
    0.06
    ries
    0.06
    inne
    0.06
     requis
    0.06
    vens
    0.06
     quantities
    0.06
     grip
    0.06
    og
    0.06
    vat
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.