© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 117914
    Prev
    Next
    INDEX
    Explanations

    patterns and structures in programming and algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Common syntax elements in technical documents, particularly punctuation following the letter "s" at line beginnings, programming keywords/operators, and mathematical notation variables.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ahkan
    -0.07
    -anchor
    -0.07
    mma
    -0.07
     ÑĦон
    -0.07
     Gui
    -0.07
     trÃŃ
    -0.06
    íĨ¡
    -0.06
    CTL
    -0.06
    iture
    -0.06
     Von
    -0.06
    POSITIVE LOGITS
    uly
    0.07
     Perkins
    0.07
    /stdc
    0.06
     robber
    0.06
     poj
    0.06
    edly
    0.06
     Lester
    0.06
    ÑĥлÑı
    0.06
     spoj
    0.06
     Friendship
    0.06
    Activations Density 0.123%

    No Known Activations