© 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. 24239
    Prev
    Next
    INDEX
    Explanations

    numerical data related to sports attendance and events

    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
    olle
    -0.19
    /Dk
    -0.15
     Abed
    -0.14
     Gef
    -0.14
     Laud
    -0.14
    amenti
    -0.14
    empo
    -0.14
    ipes
    -0.14
    amentals
    -0.14
     Duy
    -0.14
    POSITIVE LOGITS
     attendance
    0.44
     Attendance
    0.36
    Attendance
    0.34
    attendance
    0.34
     attend
    0.30
     attended
    0.27
     capacity
    0.27
     attending
    0.26
     sell
    0.24
    Capacity
    0.23
    Activations Density 0.044%

    No Known Activations