© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 39389
    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
    tra
    -0.07
     stol
    -0.06
     spl
    -0.06
    stra
    -0.06
     non
    -0.06
     Honest
    -0.06
    otel
    -0.06
     gig
    -0.05
     Experiment
    -0.05
    ande
    -0.05
    POSITIVE LOGITS
     ı
    0.08
    èĦ±
    0.07
    ovali
    0.07
    &uuml
    0.07
    å¼ĺ
    0.07
    itorio
    0.07
     Sey
    0.07
    \Migration
    0.07
    jvu
    0.07
    rez
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.