© 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. 28535
    Prev
    Next
    INDEX
    Explanations

    expressions of physical interaction and connection between characters

    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
     tongues
    -0.15
    icio
    -0.14
    leme
    -0.14
     butto
    -0.14
    Archive
    -0.14
     noses
    -0.14
    heads
    -0.14
    izi
    -0.14
     mouths
    -0.14
     Heads
    -0.14
    POSITIVE LOGITS
     own
    0.19
    ri
    0.17
    ivery
    0.15
    /Images
    0.15
     temples
    0.14
     peripherals
    0.14
     thoughts
    0.14
    '=>['
    0.13
    :num
    0.13
    rrha
    0.13
    Activations Density 0.053%

    No Known Activations