© 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. 63140
    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
    olem
    -0.07
     Mohamed
    -0.06
     Morm
    -0.06
    accessible
    -0.06
    ajas
    -0.06
    ismet
    -0.06
    ATH
    -0.06
     Sharma
    -0.06
     Advantage
    -0.06
    oret
    -0.06
    POSITIVE LOGITS
     EXEMPLARY
    0.07
    .MessageBox
    0.07
    mazon
    0.07
    æľĭ
    0.07
    ë²ķ
    0.07
    iaux
    0.06
    nila
    0.06
    ught
    0.06
    guards
    0.06
    BOVE
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.