© 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. 89657
    Prev
    Next
    INDEX
    Explanations

    past participles and verbs indicating actions related to finance, transactions, or obligations

    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
    isure
    -0.07
    xis
    -0.07
    enment
    -0.07
    iston
    -0.06
    ogie
    -0.06
    ÑĤÑĢо
    -0.06
     Tong
    -0.06
    ãĤŃ
    -0.06
    bron
    -0.06
    ÏĦÏī
    -0.06
    POSITIVE LOGITS
    itele
    0.07
    OCK
    0.06
     earlier
    0.06
    adas
    0.06
    allery
    0.06
     yesterday
    0.06
    idences
    0.06
    Locale
    0.06
    0.06
    /not
    0.06
    Activations Density 0.091%

    No Known Activations