© 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. 9-LLAMASCOPE-RES-131K
    11. 94222
    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
    าะ
    -0.07
    ová
    -0.07
    onta
    -0.07
    argin
    -0.07
    :params
    -0.07
    landing
    -0.07
     Uluslararası
    -0.07
    noon
    -0.07
    asurer
    -0.07
     пÑĢаво
    -0.07
    POSITIVE LOGITS
    ẩu
    0.06
    ádu
    0.06
    Ãłn
    0.06
     witch
    0.06
     Xu
    0.06
    á»ĵi
    0.06
     genesis
    0.06
     ì¶ľìŀ¥
    0.06
    oug
    0.06
     Singer
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.