© 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. 54330
    Prev
    Next
    INDEX
    Explanations

    phrases related to obedience and compliance to authority

    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
    elves
    -0.15
    adro
    -0.14
    æĥ
    -0.14
    Occurrences
    -0.14
    fak
    -0.13
    855
    -0.13
    ela
    -0.13
    oÄŁ
    -0.13
     guar
    -0.13
    etto
    -0.13
    POSITIVE LOGITS
     orders
    0.91
     Orders
    0.69
    orders
    0.68
     instructions
    0.68
    -orders
    0.64
     order
    0.60
    Orders
    0.58
     directions
    0.57
     instruction
    0.56
     Instructions
    0.53
    Activations Density 0.035%

    No Known Activations