© 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. 14090
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and structure in programming or script contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    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
     Highlands
    -0.07
    apat
    -0.07
    ishi
    -0.06
    é²ģ
    -0.06
    /Dk
    -0.06
     cud
    -0.06
    PTS
    -0.06
    åĬĽçļĦ
    -0.06
    SpaceItem
    -0.06
    ocz
    -0.06
    POSITIVE LOGITS
    hek
    0.06
    nee
    0.06
     Swinger
    0.06
    ker
    0.06
    onu
    0.06
    abee
    0.06
    amento
    0.06
     Cheers
    0.06
    ìĦ
    0.06
    lemen
    0.05
    Activations Density 0.091%

    No Known Activations