© 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. 91711
    Prev
    Next
    INDEX
    Explanations

    programming and scripting functions involving data manipulation and processing

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    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
    VOKE
    -0.07
    >(()
    -0.07
     Krish
    -0.07
    neh
    -0.07
     parçası
    -0.06
    irie
    -0.06
    .UnitTesting
    -0.06
    ÃĹ↵↵
    -0.06
    rys
    -0.06
    amate
    -0.06
    POSITIVE LOGITS
    (
    0.08
    /her
    0.07
    ://
    0.07
    ebek
    0.06
     Patent
    0.06
    maal
    0.06
    ((
    0.06
    ('
    0.06
    aben
    0.06
    acons
    0.06
    Activations Density 0.056%

    No Known Activations