© 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. 25181
    Prev
    Next
    INDEX
    Explanations

    references to emotional responses and sentiments regarding legal or social issues

    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
     Baltic
    -0.19
     Newark
    -0.17
     Rutgers
    -0.17
     Moose
    -0.16
     Yunan
    -0.14
     Zimbabwe
    -0.14
     Raq
    -0.14
    ilmington
    -0.14
     Vermont
    -0.14
     thyroid
    -0.14
    POSITIVE LOGITS
     Texas
    0.92
    Texas
    0.79
     Dallas
    0.78
     Texans
    0.77
     TEX
    0.74
     texas
    0.71
     TX
    0.71
     Tex
    0.68
    Dallas
    0.67
     Houston
    0.64
    Activations Density 0.053%

    No Known Activations