© 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. 86289
    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
    handleRequest
    -0.07
    ç½²
    -0.07
    lug
    -0.06
    adlo
    -0.06
    thora
    -0.06
    terra
    -0.06
     Protector
    -0.06
     æĵ
    -0.06
    lopen
    -0.06
    ngle
    -0.06
    POSITIVE LOGITS
    onto
    0.07
     duplic
    0.06
    /dd
    0.06
    580
    0.06
    Trait
    0.06
    keit
    0.06
     dz
    0.06
     Machinery
    0.05
    ichier
    0.05
    ách
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.