© 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. 104098
    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
    θÏħ
    -0.07
    ÑģÑĥÑĤ
    -0.07
    æĽ
    -0.07
     ï¼ŀ
    -0.07
     cigaret
    -0.07
    лки
    -0.07
    inalg
    -0.07
    072
    -0.07
    ,{"
    -0.07
    ëĭ¤
    -0.07
    POSITIVE LOGITS
    -
    0.07
     himself
    0.06
     to
    0.06
     neutral
    0.06
     Society
    0.06
     r
    0.06
     bibli
    0.05
    or
    0.05
    ands
    0.05
     och
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.