© 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. 29678
    Prev
    Next
    INDEX
    Explanations

    conversational phrases and references to communication methods

    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
     Years
    -0.20
     YEARS
    -0.18
    Years
    -0.17
     years
    -0.15
    undred
    -0.15
    zilla
    -0.14
     anni
    -0.14
    -years
    -0.14
     eternity
    -0.14
     textStyle
    -0.13
    POSITIVE LOGITS
     twice
    0.64
     every
    0.52
     Twice
    0.45
     daily
    0.44
     weekly
    0.44
    every
    0.39
     once
    0.39
    weekly
    0.38
    æ¯ı
    0.37
     Every
    0.37
    Activations Density 0.138%

    No Known Activations