© 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. 41606
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries related to uncertainty or clarification

    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
    IBUT
    -0.17
    ุย
    -0.15
    claim
    -0.15
    Claim
    -0.15
    RuleContext
    -0.14
    erif
    -0.14
    ган
    -0.14
     Claim
    -0.14
    acman
    -0.14
    sumer
    -0.14
    POSITIVE LOGITS
     ask
    0.67
     asked
    0.66
     asks
    0.64
    ask
    0.61
     asking
    0.58
     Ask
    0.55
    Ask
    0.54
    asks
    0.52
    ASK
    0.49
    asking
    0.48
    Activations Density 0.023%

    No Known Activations