© 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. 44100
    Prev
    Next
    INDEX
    Explanations

    terms related to energy and heat transfer processes

    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
    atas
    -0.16
     operation
    -0.15
     advance
    -0.15
     mark
    -0.14
     today
    -0.14
     aire
    -0.13
    ires
    -0.13
    itu
    -0.13
     emitting
    -0.13
     pen
    -0.13
    POSITIVE LOGITS
     through
    0.24
     via
    0.24
    through
    0.23
    via
    0.23
    sthrough
    0.21
     ÑĩеÑĢез
    0.21
    Via
    0.20
    Through
    0.20
     THROUGH
    0.20
     into
    0.20
    Activations Density 0.126%

    No Known Activations