© 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. 33488
    Prev
    Next
    INDEX
    Explanations

    words related to breathing or inhalation

    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
    a
    -0.47
    er
    -0.43
    i
    -0.43
    y
    -0.41
    o
    -0.38
    s
    -0.37
    e
    -0.37
    an
    -0.32
    à¸Ļ
    -0.30
    n
    -0.30
    POSITIVE LOGITS
    styleType
    0.18
    erece
    0.18
    abay
    0.17
    ÏĢα
    0.17
    tempts
    0.17
    forman
    0.16
    matchCondition
    0.16
    actionDate
    0.16
    $LANG
    0.16
    tep
    0.16
    Activations Density 0.037%

    No Known Activations