© 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. 15-LLAMASCOPE-RES-131K
    11. 86082
    Prev
    Next
    INDEX
    Explanations

    syntactical structures and relationships in programming languages

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    A comma or conjunction "and" that connects clauses in technical or instructional text, often appearing after input parameters or variables in function descriptions or explanations of computational processes.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219
    Triggered by @lu-christina
    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
    beck
    -0.07
    stal
    -0.07
    aine
    -0.06
     Synthetic
    -0.06
     synthetic
    -0.06
     Tune
    -0.06
    ónica
    -0.06
     Farrell
    -0.06
    erve
    -0.06
    ois
    -0.06
    POSITIVE LOGITS
    اخت
    0.07
    ÙĨØ´
    0.07
    má
    0.07
    vanished
    0.06
    avia
    0.06
    ushing
    0.06
    ribbon
    0.06
    ugin
    0.06
    Ð¡Ðł
    0.06
    alian
    0.06
    Activations Density 0.042%

    No Known Activations