© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 33301
    Prev
    Next
    INDEX
    Explanations

    phrases indicating demand or supply in a specific context

    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
     Wass
    -0.16
    ÃŃÅ¡
    -0.14
    iku
    -0.14
     Dil
    -0.14
    ÑĢади
    -0.14
    leta
    -0.14
    Uvs
    -0.14
     Dalton
    -0.14
    STANCE
    -0.13
    isclosed
    -0.13
    POSITIVE LOGITS
     demand
    1.10
     Demand
    0.94
    demand
    0.86
    Demand
    0.85
    -demand
    0.80
     demands
    0.74
    _demand
    0.68
     demanded
    0.67
     demande
    0.62
     demanding
    0.57
    Activations Density 0.036%

    No Known Activations