© 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. 24099
    Prev
    Next
    INDEX
    Explanations

    information related to sports standings and statistics

    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
    oba
    -0.17
    affen
    -0.16
    andi
    -0.15
    оба
    -0.15
    ắt
    -0.15
    rike
    -0.14
    æŃ
    -0.14
    AAD
    -0.14
    ç¥Ŀ
    -0.13
     queryInterface
    -0.13
    POSITIVE LOGITS
     sit
    0.26
     currently
    0.23
     sitting
    0.21
     lag
    0.20
     sits
    0.20
     langu
    0.20
     looking
    0.20
     idle
    0.19
     eye
    0.19
    currently
    0.19
    Activations Density 0.072%

    No Known Activations