© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 8541
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to illness and health conditions

    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
    urette
    -0.15
    lossen
    -0.15
    ITERAL
    -0.15
    odon
    -0.15
     vitae
    -0.14
    ]={↵
    -0.14
     ÅŁaÅŁ
    -0.14
    atitude
    -0.14
    asury
    -0.14
    FLICT
    -0.14
    POSITIVE LOGITS
     sick
    0.94
     Sick
    0.81
     ill
    0.79
     Ill
    0.69
     sickness
    0.65
     illness
    0.63
    Ill
    0.56
     illnesses
    0.51
    ill
    0.50
     sic
    0.38
    Activations Density 0.045%

    No Known Activations