© 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. 15410
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Bung" or related variations

    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
    er
    -0.17
    rx
    -0.17
    rs
    -0.17
    etz
    -0.17
    rm
    -0.17
    hong
    -0.16
    etto
    -0.16
    hn
    -0.16
    ç±
    -0.15
    iti
    -0.15
    POSITIVE LOGITS
    lasses
    0.22
    lish
    0.22
    su
    0.21
    sten
    0.18
    ues
    0.17
    uitar
    0.17
    redients
    0.16
    uestion
    0.16
    nam
    0.16
    ed
    0.15
    Activations Density 0.007%

    No Known Activations