© 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. 25235
    Prev
    Next
    INDEX
    Explanations

    phrases indicating requirements or introductions related to people and characters

    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
    ifax
    -0.15
    볬
    -0.14
    ivia
    -0.14
    jee
    -0.13
     impaired
    -0.13
    åıİ
    -0.13
    342
    -0.13
    adle
    -0.13
    irling
    -0.13
    axter
    -0.13
    POSITIVE LOGITS
     introduction
    1.34
     introdu
    1.30
     introduced
    1.20
     introduce
    1.19
     Introduction
    1.15
     intro
    1.10
     introducing
    1.08
    Introduction
    1.07
     introduces
    1.04
     Introduced
    1.04
    Activations Density 0.013%

    No Known Activations