© 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. 14104
    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
    uzzi
    -0.07
     Bes
    -0.07
    (Optional
    -0.06
    ÅĽnie
    -0.06
    ury
    -0.06
    reative
    -0.06
    iliz
    -0.06
    Incre
    -0.06
    él
    -0.06
    arios
    -0.06
    POSITIVE LOGITS
     Balt
    0.07
    inki
    0.07
    заб
    0.07
     Eston
    0.07
    .lt
    0.07
    çĪµ
    0.07
     Ki
    0.07
    __,__
    0.07
    æk
    0.07
    umber
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.