© 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. 17-LLAMASCOPE-RES-131K
    11. 89687
    Prev
    Next
    INDEX
    Explanations

    configuration files and settings related to a software system

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

    HTML/XML closing tags, attribute declarations, or code syntax elements like dots before property/variable names in programming contexts.

    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
    .MixedReality
    -0.09
    antity
    -0.08
    redicate
    -0.07
    rvé
    -0.07
    .IContainer
    -0.07
    гал
    -0.07
    olley
    -0.07
    ngth
    -0.07
    iali
    -0.07
    ongan
    -0.07
    POSITIVE LOGITS
     autoc
    0.06
    580
    0.06
    .bundle
    0.05
     rend
    0.05
    erna
    0.05
     Gordon
    0.05
    omatic
    0.05
     Dodd
    0.05
     itself
    0.05
    /language
    0.05
    Activations Density 0.112%

    No Known Activations