© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 14708
    Prev
    Next
    INDEX
    Explanations

    references to health risks and associated mortality statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    gated
    Context Size
    1,024
    Dataset
    Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bay
    -0.15
     profil
    -0.15
     reusable
    -0.14
     tat
    -0.13
     tuy
    -0.13
     Huff
    -0.13
     sang
    -0.13
    æį
    -0.13
    аÑĤкÑĥ
    -0.12
    ackbar
    -0.12
    POSITIVE LOGITS
     mortality
    0.31
     death
    0.29
     Mort
    0.27
    death
    0.23
     deaths
    0.22
     incident
    0.22
    -death
    0.22
     cardiovascular
    0.22
    _death
    0.21
     morality
    0.21
    Activations Density 0.066%

    No Known Activations