© 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. 63182
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions and events related to driving and movement

    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
    _PUSHDATA
    -0.17
    avax
    -0.16
     EntryPoint
    -0.15
    inode
    -0.14
     dall
    -0.14
    ereum
    -0.14
    oken
    -0.14
    isky
    -0.14
    ulse
    -0.13
    .createFrom
    -0.13
    POSITIVE LOGITS
     en
    0.77
     headed
    0.47
     heading
    0.42
     bound
    0.40
     on
    0.36
     route
    0.35
     En
    0.34
    En
    0.34
    Heading
    0.33
     Heading
    0.32
    Activations Density 0.032%

    No Known Activations