© 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. 108700
    Prev
    Next
    INDEX
    Explanations

    occurrences of JavaScript function declarations and invocations

    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
    recision
    -0.06
    ataka
    -0.06
    mite
    -0.06
    ,
    -0.06
    ovit
    -0.06
    idan
    -0.06
     vos
    -0.06
    liced
    -0.05
    rowned
    -0.05
     Americ
    -0.05
    POSITIVE LOGITS
    à¹ĥà¸Ī
    0.07
    MinMax
    0.07
    ãĥIJãĥ¼
    0.07
    OOT
    0.07
    许
    0.06
    ">//
    0.06
    .scalablytyped
    0.06
    ома
    0.06
    ugin
    0.06
     herk
    0.06
    Activations Density 0.003%

    No Known Activations