© 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. 63343
    Prev
    Next
    INDEX
    Explanations

    phrases indicating obligations or requirements

    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
    TOT
    -0.16
    aze
    -0.15
    usta
    -0.15
    रण
    -0.14
    ãĥģãĥ¥
    -0.13
    uka
    -0.13
    _pas
    -0.13
    ERE
    -0.13
    ListGroup
    -0.13
     Sylv
    -0.13
    POSITIVE LOGITS
     to
    0.41
     να
    0.21
    to
    0.20
    	to
    0.20
     by
    0.17
    GenerationStrategy
    0.17
     tp
    0.16
    GuidId
    0.15
    ëªħìĿĦ
    0.15
     Äijá»ĥ
    0.15
    Activations Density 0.097%

    No Known Activations