© 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. 41708
    Prev
    Next
    INDEX
    Explanations

    components and syntax related to mathematical expressions and calculations

    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
    es
    -0.17
    las
    -0.17
    obus
    -0.15
    inde
    -0.15
    deaux
    -0.15
    볨
    -0.14
    acter
    -0.14
    ä½į
    -0.14
    ç¿
    -0.13
    aux
    -0.13
    POSITIVE LOGITS
    display
    0.26
     display
    0.26
     Display
    0.22
    -display
    0.22
    Display
    0.21
     DISPLAY
    0.21
    _display
    0.20
    isplay
    0.20
     displays
    0.20
    .display
    0.19
    Activations Density 0.024%

    No Known Activations