© 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. 80836
    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
    Not in Any Lists

    No Comments

    Negative Logits
    rak
    -0.07
     ragaz
    -0.07
    еÑĢа
    -0.07
    defs
    -0.07
    uga
    -0.07
    iga
    -0.07
    isc
    -0.07
     definitely
    -0.07
    DataTable
    -0.06
    udu
    -0.06
    POSITIVE LOGITS
     Von
    0.06
     orig
    0.06
     TArray
    0.06
    çŃĨ
    0.06
     fe
    0.06
     již
    0.06
    voir
    0.06
    ance
    0.06
    ानन
    0.06
    aisy
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.