© 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. 21956
    Prev
    Next
    INDEX
    Explanations

    references to divorce-related statistics and legal aspects

    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
    cone
    -0.14
    olan
    -0.14
    ictim
    -0.13
     chall
    -0.13
    InputLabel
    -0.13
    CHIP
    -0.13
    ropdown
    -0.13
    .EVENT
    -0.13
     hob
    -0.13
    ÏĥÏī
    -0.13
    POSITIVE LOGITS
     divorce
    0.71
     Div
    0.70
    Div
    0.63
     divor
    0.60
    -div
    0.59
     divorced
    0.59
     DIV
    0.58
    div
    0.57
     div
    0.55
     separation
    0.55
    Activations Density 0.053%

    No Known Activations