© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29616
    Prev
    Next
    INDEX
    Explanations

    references to marathons and seminars

    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
     thôi
    -0.16
    anko
    -0.16
     çĤ¹åĩ»
    -0.15
    fur
    -0.15
    semblies
    -0.15
     addCriterion
    -0.15
    ">ÃĹ</
    -0.15
    /**č↵
    -0.14
     eskort
    -0.14
    irket
    -0.14
    POSITIVE LOGITS
    -style
    0.25
     style
    0.23
     participants
    0.21
     format
    0.19
    urs
    0.19
    ee
    0.18
    ize
    0.18
     room
    0.18
    -winning
    0.18
     rooms
    0.18
    Activations Density 0.007%

    No Known Activations