© 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. 15-LLAMASCOPE-RES-131K
    11. 86050
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific brand-related terms

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

    Terminal word components that complete proper names, brands, or technical terms, often serving as the distinguishing identifier within compound names.

    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
    خش
    -0.06
    елÑĸ
    -0.06
    ichert
    -0.06
     Dow
    -0.06
    loi
    -0.06
    豪
    -0.06
    ono
    -0.06
    acf
    -0.06
    afc
    -0.06
    ано
    -0.06
    POSITIVE LOGITS
     army
    0.07
     Army
    0.07
     Agenda
    0.07
    dden
    0.07
     |--------------------------------------------------------------------------↵
    0.07
    ernational
    0.06
    gend
    0.06
     buflen
    0.06
    .appspot
    0.06
    #
    0.06
    Activations Density 0.063%

    No Known Activations