© 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. 116544
    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
    503
    -0.06
    otch
    -0.06
    afia
    -0.06
     devs
    -0.06
    805
    -0.06
    'gc
    -0.06
     lapse
    -0.06
    wie
    -0.06
    :UITableView
    -0.06
    907
    -0.05
    POSITIVE LOGITS
    ixels
    0.08
     dược
    0.07
    istes
    0.07
     latter
    0.07
    izmet
    0.07
    .vs
    0.07
    quist
    0.07
    adem
    0.07
    chk
    0.07
    cad
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.