© 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. 116622
    Prev
    Next
    INDEX
    Explanations

    instances of personal pronouns and references to inquiries or requests

    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
    ÏģιÏĥÏĦ
    -0.07
     Norris
    -0.07
     nostr
    -0.06
    iddles
    -0.06
    sburg
    -0.06
     Reader
    -0.06
    ska
    -0.06
    anax
    -0.06
    mania
    -0.06
    ellen
    -0.06
    POSITIVE LOGITS
    견
    0.07
    .binding
    0.06
    ä
    0.06
    208
    0.06
    brig
    0.06
    inite
    0.06
    eon
    0.06
    MLS
    0.06
    rium
    0.06
    inia
    0.06
    Activations Density 0.001%

    No Known Activations