© 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 EvalsExportsinterp-engineNEWAPI 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. 44876
    Prev
    Next
    INDEX
    Explanations

    references to legal actions regarding domestic violence situations

    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
     Prison
    -0.16
    LAG
    -0.15
     prisoners
    -0.15
     prisoner
    -0.15
    utron
    -0.14
     detainees
    -0.14
     Rat
    -0.14
    มà¸Ļ
    -0.14
    Ñıм
    -0.14
    ieren
    -0.13
    POSITIVE LOGITS
     restraining
    0.33
     Restr
    0.31
    Restr
    0.28
     orders
    0.25
    Protection
    0.25
     Protection
    0.24
     Orders
    0.24
     stalking
    0.24
     restr
    0.24
    Orders
    0.23
    Activations Density 0.020%

    No Known Activations