© 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. 31608
    Prev
    Next
    INDEX
    Explanations

    elements related to programming language syntax and data structure validation

    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
    (æľ¨
    -0.09
    ntax
    -0.08
    ÑĪин
    -0.08
    ailles
    -0.07
    aille
    -0.07
    xaf
    -0.07
    ierce
    -0.07
    -INF
    -0.07
    /Gate
    -0.07
    kees
    -0.07
    POSITIVE LOGITS
    ,
    0.08
    ãĢįãĢĮ
    0.08
    ãĢģ
    0.06
    verse
    0.06
    ?,
    0.06
    /*
    0.06
    ;
    0.06
    *,
    0.05
    ={},
    0.05
     vs
    0.05
    Activations Density 0.063%

    No Known Activations