© 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. 29213
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal regulations and 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
    antino
    -0.13
    :params
    -0.13
     Decompiled
    -0.13
    Ｌ
    -0.13
    olah
    -0.13
    ucas
    -0.13
    Fcn
    -0.13
    ivec
    -0.12
    -Za
    -0.12
     ngÄĥn
    -0.12
    POSITIVE LOGITS
     requirement
    0.76
     required
    0.76
     require
    0.74
     requiring
    0.68
    require
    0.68
     requires
    0.66
     requirements
    0.66
     Require
    0.65
     Requirement
    0.64
     Required
    0.63
    Activations Density 0.043%

    No Known Activations