© 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. 15-LLAMASCOPE-RES-131K
    11. 87472
    Prev
    Next
    INDEX
    Explanations

    fragments of code and programming constructs related to function definitions and parameters

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

    Conditional statements that check for the existence of specific parameters in command parsing, often following the pattern "if (code_seen('X'))" where X is a parameter identifier.

    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
    ijn
    -0.07
    á»ķ
    -0.06
     safest
    -0.05
     Corner
    -0.05
    ht
    -0.05
    oker
    -0.05
    Rep
    -0.05
    adu
    -0.05
     Braun
    -0.05
    ãng
    -0.05
    POSITIVE LOGITS
     arity
    0.09
    istrovstvÃŃ
    0.09
    pais
    0.07
     $#
    0.07
    argc
    0.07
     argc
    0.07
    ازÙħ
    0.07
    gue
    0.07
    escription
    0.07
    .getLength
    0.07
    Activations Density 0.133%

    No Known Activations