© 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. 89769
    Prev
    Next
    INDEX
    Explanations

    keywords related to vehicle accidents and types of trucks involved

    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
    Gun
    -0.07
    nett
    -0.07
     action
    -0.07
    753
    -0.07
    onaut
    -0.06
    ering
    -0.06
     hosts
    -0.06
    otts
    -0.06
     Gun
    -0.06
     Fut
    -0.06
    POSITIVE LOGITS
     Palette
    0.07
    ValueCollection
    0.07
     kiá»ĩn
    0.07
    ýn
    0.07
    лаб
    0.07
     trailer
    0.07
     bufferSize
    0.07
    panic
    0.07
    ạch
    0.06
    ieux
    0.06
    Activations Density 0.012%

    No Known Activations