© 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. 42355
    Prev
    Next
    INDEX
    Explanations

    citations and references to sources or data in the text

    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
    ัà¸Ħ
    -0.13
     latter
    -0.13
    наÑĩе
    -0.13
    quired
    -0.13
    ÑĹ
    -0.12
     eskort
    -0.12
    едÑĮ
    -0.12
    oub
    -0.12
    ãģķãĤīãģ«
    -0.12
    <<<
    -0.12
    POSITIVE LOGITS
     https
    0.17
    https
    0.17
    éľ
    0.15
     "
    0.15
     http
    0.14
    reater
    0.14
     Various
    0.13
    ctal
    0.13
    acman
    0.13
    unn
    0.12
    Activations Density 0.183%

    No Known Activations