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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 62240
    Prev
    Next
    INDEX
    Explanations

    keywords and parameters related to software configuration and technical specifications

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

    Technical tokens that appear in programming code, logging statements, or URL paths, often representing function names, variable identifiers or file system references.

    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
    iyan
    -0.07
    emand
    -0.07
    ergy
    -0.07
    quirrel
    -0.07
    arse
    -0.06
    credible
    -0.06
    dzi
    -0.06
     taste
    -0.06
    ühl
    -0.06
    apas
    -0.06
    POSITIVE LOGITS
    Directions
    0.06
    .dylib
    0.06
    roman
    0.06
     $($
    0.06
     Garland
    0.06
    antz
    0.06
    .↵↵↵↵↵↵↵↵
    0.06
    matches
    0.06
    ISCO
    0.06
    
    0.06
    Activations Density 0.107%

    No Known Activations