© 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. 28990
    Prev
    Next
    INDEX
    Explanations

    instances of suffering or distress related to injuries and physical conditions

    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
     Twelve
    -0.18
    ioxide
    -0.17
    teenth
    -0.16
    eenth
    -0.15
     ele
    -0.14
    uther
    -0.14
     nineteenth
    -0.13
     Eleven
    -0.13
    æĽ°
    -0.13
     ($
    -0.13
    POSITIVE LOGITS
     half
    0.53
     HALF
    0.46
    half
    0.44
    70
    0.42
    75
    0.41
     Half
    0.41
    85
    0.40
    80
    0.40
    Half
    0.39
    50
    0.39
    Activations Density 0.110%

    No Known Activations