© 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. 38427
    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
    erc
    -0.07
    requ
    -0.06
    engeance
    -0.06
    uffs
    -0.06
    pare
    -0.06
    eson
    -0.06
     '">
    -0.06
    ipse
    -0.06
    ighton
    -0.06
    ency
    -0.06
    POSITIVE LOGITS
    antro
    0.08
     vX
    0.07
     moms
    0.07
     evangel
    0.07
     former
    0.06
    Æ°á»Ľng
    0.06
    onis
    0.06
     everybody
    0.06
     ann
    0.06
     clr
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.