© 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. 28362
    Prev
    Next
    INDEX
    Explanations

    variations of the name "Shue."

    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
     stretch
    -0.16
     bill
    -0.16
     Bill
    -0.15
    stown
    -0.15
     Stretch
    -0.15
    rine
    -0.15
    emble
    -0.14
    Ëĺ
    -0.14
    orgia
    -0.14
    ór
    -0.14
    POSITIVE LOGITS
    burgh
    0.17
    ichi
    0.17
    oxid
    0.16
    ãĥ¼ãĤ¿ãĥ¼
    0.16
    wit
    0.15
    maker
    0.15
    UILTIN
    0.15
    ways
    0.14
    nicas
    0.14
    way
    0.14
    Activations Density 0.004%

    No Known Activations