© 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. 69297
    Prev
    Next
    INDEX
    Explanations

    function definitions and mathematical computations in programming code

    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
    htags
    -0.07
    .scalablytyped
    -0.07
    .createNew
    -0.06
    htag
    -0.06
     ÎĶε
    -0.06
    گاÙĨ
    -0.06
    ActionCreators
    -0.06
     Beg
    -0.06
    ?↵↵↵↵
    -0.06
     доÑĢ
    -0.06
    POSITIVE LOGITS
    nip
    0.07
    aine
    0.07
    above
    0.06
    insic
    0.06
    san
    0.06
    asia
    0.06
    adge
    0.06
    bjerg
    0.06
    _MAGIC
    0.06
    lauf
    0.06
    Activations Density 0.012%

    No Known Activations