© 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. 91781
    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
    Eval
    -0.07
     tslib
    -0.07
    ATEGORIES
    -0.07
    Reuse
    -0.07
    arton
    -0.07
     Ley
    -0.07
    ROTO
    -0.07
    à¹į
    -0.07
    غÙĨ
    -0.06
    746
    -0.06
    POSITIVE LOGITS
    ifik
    0.07
    pekt
    0.07
    ello
    0.06
    peg
    0.06
     peg
    0.06
    Äĩ
    0.06
    uzzi
    0.06
    amping
    0.05
    odi
    0.05
    ;s
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.