© 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. 54810
    Prev
    Next
    INDEX
    Explanations

    significant names and expressions of emotion or action in a narrative context

    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
    enor
    -0.14
    Įĵ
    -0.14
    MAND
    -0.13
    ocs
    -0.13
    ($(".
    -0.13
     Pace
    -0.13
    pard
    -0.13
    opsis
    -0.12
    owler
    -0.12
    мп
    -0.12
    POSITIVE LOGITS
     pointing
    1.03
     pointed
    0.98
     pointer
    0.84
     pointers
    0.82
     point
    0.81
     Point
    0.80
    æĮĩ
    0.80
    -point
    0.76
    point
    0.73
     Pointer
    0.71
    Activations Density 0.011%

    No Known Activations