© 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. 21749
    Prev
    Next
    INDEX
    Explanations

    references to Alzheimer's disease and cognitive impairments

    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
     pediatric
    -0.14
    sted
    -0.14
     prost
    -0.14
    chez
    -0.14
    éijij
    -0.14
    éĺ
    -0.14
    ORTH
    -0.14
    orsi
    -0.13
     congen
    -0.13
     pelvic
    -0.13
    POSITIVE LOGITS
     Alzheimer
    0.45
     dementia
    0.37
     brains
    0.33
     amy
    0.32
    ementia
    0.32
     brain
    0.31
     tau
    0.30
    zheimer
    0.29
     Brain
    0.27
     memory
    0.27
    Activations Density 0.005%

    No Known Activations