© 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. 15539
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of individuals

    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
    ãĤ§
    -0.16
    give
    -0.16
    زش
    -0.16
    owing
    -0.16
    ãĤį
    -0.15
    $MESS
    -0.14
    Ãłng
    -0.14
    िà¤ķत
    -0.14
    Å¡ÃŃm
    -0.14
    ุà¸ļ
    -0.14
    POSITIVE LOGITS
    adays
    0.45
    odore
    0.43
    etheless
    0.38
    achusetts
    0.36
    jamin
    0.33
    atre
    0.32
    ellaneous
    0.32
    greSQL
    0.32
    gerald
    0.31
    quarters
    0.31
    Activations Density 0.126%

    No Known Activations