© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 25882
    Prev
    Next
    INDEX
    Explanations

    details related to paid leave policies and healthcare coverage

    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
    ulle
    -0.16
     Qed
    -0.16
    ÑħÑĥ
    -0.15
    plevel
    -0.15
    мон
    -0.15
    ampo
    -0.15
     voksne
    -0.14
    .manual
    -0.14
    éłĨ
    -0.14
    ynos
    -0.13
    POSITIVE LOGITS
     leave
    0.42
     Paid
    0.38
     paid
    0.36
     Leave
    0.36
    Leave
    0.34
    leave
    0.33
    Paid
    0.33
     sick
    0.33
     leaves
    0.32
     Sick
    0.31
    Activations Density 0.021%

    No Known Activations