© 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. 42894
    Prev
    Next
    INDEX
    Explanations

    references to laws and regulations surrounding medical practices

    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
     Asi
    -0.14
    Suppress
    -0.14
    rott
    -0.14
    à¥įवप
    -0.14
     ());↵↵
    -0.14
    ritz
    -0.14
    PageIndex
    -0.14
    strtotime
    -0.14
    å°ıåѦ
    -0.14
    iktig
    -0.14
    POSITIVE LOGITS
     terminal
    0.34
     termin
    0.32
     Terminal
    0.32
     pall
    0.32
     dying
    0.30
     Pall
    0.30
    terminal
    0.28
     euth
    0.27
     assisted
    0.27
    Terminal
    0.26
    Activations Density 0.033%

    No Known Activations