© 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. 55135
    Prev
    Next
    INDEX
    Explanations

    demographic statistics and trends related to young adults and health insurance

    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
    agas
    -0.16
    dings
    -0.15
    unik
    -0.15
    urat
    -0.14
    prox
    -0.14
    äs
    -0.14
     tslib
    -0.13
    omin
    -0.13
    unday
    -0.13
    ERIC
    -0.13
    POSITIVE LOGITS
     aged
    0.73
     ages
    0.67
     age
    0.56
     between
    0.56
     Ages
    0.51
    between
    0.47
    aged
    0.45
    -aged
    0.44
     Between
    0.44
     Age
    0.44
    Activations Density 0.081%

    No Known Activations