© 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. 44713
    Prev
    Next
    INDEX
    Explanations

    mentions of technology and its applications, particularly in IoT and e-commerce

    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
     Yates
    -0.18
    cznie
    -0.15
    æķı
    -0.15
    itched
    -0.15
    ÑĢеб
    -0.15
    otre
    -0.14
     WithEvents
    -0.14
    Ðİ
    -0.14
    isel
    -0.14
    hoe
    -0.14
    POSITIVE LOGITS
     revolution
    0.25
     Revolution
    0.24
     pioneer
    0.22
     solutions
    0.21
     technologies
    0.20
     market
    0.19
     applications
    0.19
     adoption
    0.18
     platforms
    0.17
     Pioneer
    0.17
    Activations Density 0.089%

    No Known Activations