© 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. 42392
    Prev
    Next
    INDEX
    Explanations

    references to ticket sales and event promotions

    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
    inox
    -0.16
     Ratings
    -0.15
     accession
    -0.14
    ë°±
    -0.14
     contents
    -0.13
     entreg
    -0.13
     ult
    -0.13
    ì±Ħ
    -0.13
    ratings
    -0.12
     trä
    -0.12
    POSITIVE LOGITS
     ticket
    0.65
     Ticket
    0.60
     tickets
    0.59
     Tickets
    0.53
    Ticket
    0.50
    Tickets
    0.49
    -ticket
    0.49
    ticket
    0.48
     TICK
    0.45
    tickets
    0.44
    Activations Density 0.059%

    No Known Activations