© 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. 18718
    Prev
    Next
    INDEX
    Explanations

    phrases related to severe weather events, particularly hurricanes, and their impacts

    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
    mony
    -0.07
    оÑĢи
    -0.06
     putas
    -0.06
     karak
    -0.06
    ecom
    -0.06
     stumbling
    -0.06
    ê¸Ī
    -0.06
     모르
    -0.06
    .MODE
    -0.06
     thông
    -0.06
    POSITIVE LOGITS
    icz
    0.08
     remembered
    0.07
     infamous
    0.07
     memorable
    0.07
     record
    0.07
    ade
    0.07
     occurred
    0.06
    occ
    0.06
     Reference
    0.06
    roid
    0.06
    Activations Density 0.012%

    No Known Activations