© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 23812
    Prev
    Next
    INDEX
    Explanations

    references to safety regulations and compliance

    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
    SizePolicy
    -0.13
    isman
    -0.13
    kap
    -0.13
    ิà¸Ĺà¸ĺ
    -0.13
     addslashes
    -0.12
    stances
    -0.12
    Views
    -0.12
    neau
    -0.12
     tab
    -0.12
    uations
    -0.12
    POSITIVE LOGITS
     goals
    0.81
     goal
    0.75
     Goals
    0.69
     objectives
    0.66
    goals
    0.63
     Goal
    0.62
    Goals
    0.60
    goal
    0.59
    Goal
    0.55
    -goal
    0.53
    Activations Density 0.065%

    No Known Activations