© 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. 63481
    Prev
    Next
    INDEX
    Explanations

    sections marked by a specific format or code, possibly representing important or highlighted content

    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
    stagram
    -0.14
    antry
    -0.14
    /******/
    -0.14
     Invest
    -0.14
    ĶåĽŀ
    -0.14
    è¿ĺæĺ¯
    -0.14
    Intialized
    -0.13
    _kses
    -0.13
     Investments
    -0.13
    #SBATCH
    -0.13
    POSITIVE LOGITS
    itele
    0.15
    001
    0.14
    errMsg
    0.14
    éri
    0.14
    âĢª
    0.14
    version
    0.13
    abox
    0.13
    .Version
    0.13
    anki
    0.13
    aka
    0.13
    Activations Density 0.006%

    No Known Activations