© 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. 55382
    Prev
    Next
    INDEX
    Explanations

    terms related to immune responses and infections

    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
    945
    -0.17
    rych
    -0.15
     Blaze
    -0.15
    ornado
    -0.15
     éļ
    -0.15
     Fen
    -0.15
     antid
    -0.14
    reck
    -0.14
    fen
    -0.14
    avin
    -0.14
    POSITIVE LOGITS
     pathogens
    0.30
     path
    0.27
    path
    0.25
     diseases
    0.25
     threats
    0.24
     Agents
    0.24
     agents
    0.23
    -path
    0.22
    agents
    0.22
     infectious
    0.21
    Activations Density 0.032%

    No Known Activations