© 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. 44663
    Prev
    Next
    INDEX
    Explanations

    references to regulatory policies and actions, particularly those associated with the Trump administration

    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
     xrange
    -0.16
    iPad
    -0.14
    .userInteractionEnabled
    -0.14
    kaç
    -0.14
     депÑĥÑĤ
    -0.13
     Occupy
    -0.13
    uries
    -0.13
     Kinect
    -0.13
     haute
    -0.13
     ipad
    -0.13
    POSITIVE LOGITS
     Trump
    0.50
    Trump
    0.43
     Donald
    0.34
    -Trump
    0.33
     Ivanka
    0.29
     White
    0.28
    Donald
    0.28
     President
    0.26
     executive
    0.25
     Melania
    0.25
    Activations Density 0.058%

    No Known Activations