© 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. 24940
    Prev
    Next
    INDEX
    Explanations

    phrases related to vehicle and driver identification information

    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
     Belfast
    -0.17
     Nairobi
    -0.16
     Manila
    -0.15
     downtown
    -0.15
    Americ
    -0.15
     Prague
    -0.15
    celona
    -0.14
    .nasa
    -0.14
     Islamabad
    -0.14
    stoff
    -0.14
    POSITIVE LOGITS
     Georgia
    0.49
     Pennsylvania
    0.48
     Michigan
    0.48
     Illinois
    0.47
     Texas
    0.45
     Massachusetts
    0.44
     California
    0.43
     Maryland
    0.43
     Ohio
    0.43
     Florida
    0.43
    Activations Density 0.138%

    No Known Activations