© 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. 32982
    Prev
    Next
    INDEX
    Explanations

    references to coffee consumption and its effects on users

    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
     eldre
    -0.18
    iese
    -0.17
    azzi
    -0.16
    оÑĢом
    -0.16
    letics
    -0.15
    bgcolor
    -0.15
    TRA
    -0.15
    öst
    -0.15
    licit
    -0.14
    YTE
    -0.13
    POSITIVE LOGITS
     heavy
    0.41
     Heavy
    0.37
    heavy
    0.36
    Heavy
    0.35
     heavier
    0.29
     frequent
    0.28
     regular
    0.28
    -heavy
    0.27
     occasional
    0.25
    regular
    0.24
    Activations Density 0.028%

    No Known Activations