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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 87671
    Prev
    Next
    INDEX
    Explanations

    programming concepts related to functions and state management

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

    Programming syntax elements appearing within nested expressions, particularly in conditional statements, array indexing, and mathematical operations.

    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
    Ä°L
    -0.08
    zar
    -0.06
     Nex
    -0.06
     seh
    -0.06
    eur
    -0.06
    Ưá»
    -0.06
    thur
    -0.06
    otec
    -0.06
    ÑĢÑĸ
    -0.06
     Dice
    -0.06
    POSITIVE LOGITS
    addon
    0.07
    argout
    0.06
    isson
    0.06
    heits
    0.06
     seul
    0.06
    olec
    0.06
     Joi
    0.06
    çĽijåIJ¬é¡µéĿ¢
    0.06
    bjerg
    0.06
    istrovstvÃŃ
    0.06
    Activations Density 0.289%

    No Known Activations