© 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. 8829
    Prev
    Next
    INDEX
    Explanations

    discussions regarding player transfers and team performance

    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
    itial
    -0.17
    TypeID
    -0.15
    é¼
    -0.15
     $('#'
    -0.15
     libertine
    -0.15
     Sche
    -0.14
     ugl
    -0.14
     ske
    -0.14
    алÑĮ
    -0.13
     Neighbor
    -0.13
    POSITIVE LOGITS
     VAR
    0.18
     Mystic
    0.17
     Fixture
    0.17
    kip
    0.17
     Transfer
    0.17
    keyboard
    0.16
     Premier
    0.16
     Sky
    0.16
     fixture
    0.16
     MOT
    0.15
    Activations Density 0.181%

    No Known Activations