© 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. 1223
    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
    Negative Logits
    ÂĿ
    -0.07
    urum
    -0.07
    anio
    -0.07
    ÅĽ
    -0.07
    alıdır
    -0.07
     immigr
    -0.06
    梨
    -0.06
     ($.
    -0.06
    ansa
    -0.06
    @foreach
    -0.06
    POSITIVE LOGITS
    oh
    0.07
     overall
    0.07
    ÃŃrk
    0.06
     Leone
    0.06
    etc
    0.06
     etc
    0.06
    iani
    0.06
    argas
    0.06
     Ey
    0.06
     stuff
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.