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

    Neuronpedia

    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. 41988
    Prev
    Next
    INDEX
    Explanations

    topics related to healthcare and associated organizations

    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
     Jub
    -0.17
    .radioButton
    -0.15
    PCODE
    -0.14
    @student
    -0.14
    ØŃت
    -0.14
    ebi
    -0.13
    аÑĢÑĩ
    -0.13
    Nonce
    -0.12
     adb
    -0.12
    ushman
    -0.12
    POSITIVE LOGITS
    .com
    0.69
    .org
    0.55
    .net
    0.47
    .COM
    0.47
    .co
    0.35
    .Com
    0.35
    .gov
    0.34
     com
    0.32
    com
    0.32
    .io
    0.31
    Activations Density 0.042%

    No Known Activations