© 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. 91855
    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
    .Metro
    -0.08
    atel
    -0.08
     Equality
    -0.07
    ãģķãģĦ
    -0.07
    blogs
    -0.07
    Equality
    -0.06
    rawn
    -0.06
    ustum
    -0.06
    еÑĢжав
    -0.06
    iffin
    -0.06
    POSITIVE LOGITS
     Robbins
    0.07
     rob
    0.07
     Rob
    0.06
    گز
    0.06
    main
    0.06
     nowhere
    0.06
     main
    0.06
    piler
    0.06
    же
    0.06
     Gala
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.