© 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. 91753
    Prev
    Next
    INDEX
    Explanations

    occurrences of impactful events or incidents, particularly disasters or strikes

    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
    wick
    -0.07
    oints
    -0.07
    ajo
    -0.06
    ลาย
    -0.06
    زÙĪ
    -0.06
     Fut
    -0.06
     Wheeler
    -0.06
    еÑģÑĤи
    -0.06
    à¸Ķà¸ĩ
    -0.06
    enties
    -0.06
    POSITIVE LOGITS
     PROCUREMENT
    0.07
     us
    0.07
    ÑģÑĭл
    0.06
    cth
    0.06
     parts
    0.06
     America
    0.06
    á»ķ
    0.06
    flush
    0.06
    resh
    0.06
    QT
    0.06
    Activations Density 0.011%

    No Known Activations