© 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. 18821
    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
    uyo
    -0.07
     elev
    -0.07
     Provid
    -0.06
     elevation
    -0.06
    opp
    -0.06
    abile
    -0.06
    uil
    -0.06
    .cleanup
    -0.06
     Deniz
    -0.06
     guys
    -0.06
    POSITIVE LOGITS
    ipi
    0.08
     ÎĶε
    0.08
    238
    0.07
    aca
    0.07
    icken
    0.07
    andon
    0.06
    elerinden
    0.06
    elson
    0.06
    -css
    0.06
    æĽ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.