© 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. 25274
    Prev
    Next
    INDEX
    Explanations

    references to political affiliations and party dynamics

    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
    _Parameter
    -0.15
    OUSE
    -0.15
    Inspectable
    -0.15
    //{{
    -0.15
    ">//
    -0.14
    drv
    -0.14
    \application
    -0.14
    IXEL
    -0.14
    lahoma
    -0.13
    (Pointer
    -0.13
    POSITIVE LOGITS
     Republican
    0.53
     Republicans
    0.48
     Democrats
    0.46
     Democratic
    0.46
     Democrat
    0.45
    Republican
    0.39
     Republic
    0.39
    Democrats
    0.35
    Democratic
    0.33
     GOP
    0.33
    Activations Density 0.069%

    No Known Activations