© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 28125
    Prev
    Next
    INDEX
    Explanations

    instances of significant changes or transformations in relation to sports fandom and participation

    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
    ÙĨز
    -0.15
    iyel
    -0.13
    ÃŃÅ¡
    -0.12
    rades
    -0.12
    é½
    -0.12
    !=(
    -0.12
    .OnItemClickListener
    -0.11
    eyle
    -0.11
     bunların
    -0.11
     intervening
    -0.11
    POSITIVE LOGITS
     SUCH
    0.15
    "is
    0.14
     such
    0.14
    such
    0.14
    ddf
    0.13
    aso
    0.13
    ÑĥлÑİ
    0.13
    .metamodel
    0.13
    via
    0.13
    exels
    0.13
    Activations Density 0.011%

    No Known Activations