© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 8706
    Prev
    Next
    INDEX
    Explanations

    phrases related to player rankings and evaluations in sports

    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
    (çģ«
    -0.17
    lope
    -0.16
    ogne
    -0.15
    emer
    -0.15
    aniem
    -0.14
    šak
    -0.14
    }elseif
    -0.14
    ìŀ¥ìĿĢ
    -0.14
    inia
    -0.13
    Segue
    -0.13
    POSITIVE LOGITS
     draft
    0.47
     drafted
    0.39
     Draft
    0.36
    draft
    0.34
    Draft
    0.33
     drafting
    0.32
     dra
    0.30
     drafts
    0.30
     pick
    0.29
     picks
    0.26
    Activations Density 0.093%

    No Known Activations