© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 28444
    Prev
    Next
    INDEX
    Explanations

    references to gunshot injuries and their locations on the body

    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
    .toolbox
    -0.15
     noses
    -0.15
    andalone
    -0.14
     Fault
    -0.14
    ocale
    -0.14
    swith
    -0.14
    esini
    -0.14
    าà¸ķร
    -0.14
    acht
    -0.13
    è¡Ľ
    -0.13
    POSITIVE LOGITS
     leg
    0.30
     chest
    0.25
     right
    0.24
     upper
    0.24
     left
    0.23
     arm
    0.21
     legs
    0.21
     abdomen
    0.21
     Chest
    0.20
     torso
    0.20
    Activations Density 0.022%

    No Known Activations