© 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. 121338
    Prev
    Next
    INDEX
    Explanations

    words or phrases that denote a sense of community engagement or participation

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    .gc
    -0.08
    /xhtml
    -0.07
     norge
    -0.07
    istrovstvÃŃ
    -0.07
    ¥IJ
    -0.07
    ãĤ¡
    -0.07
    DEX
    -0.07
    (Py
    -0.06
     hete
    -0.06
     lod
    -0.06
    POSITIVE LOGITS
     neighborhood
    0.07
    ?url
    0.06
     Citizens
    0.06
     project
    0.06
     water
    0.06
     Friends
    0.06
     Grimm
    0.06
     Conservation
    0.06
    ours
    0.06
     Municip
    0.06
    Activations Density 0.000%

    No Known Activations