© 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. 13982
    Prev
    Next
    INDEX
    Explanations

    details about genetic components and autoimmune diseases

    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
     lesb
    -0.15
    olina
    -0.14
     beden
    -0.14
    achte
    -0.13
    åĢ«
    -0.13
    IBE
    -0.13
    /animate
    -0.13
    oler
    -0.13
    FLAG
    -0.13
    ufe
    -0.13
    POSITIVE LOGITS
     her
    0.48
     inherited
    0.42
     genetics
    0.41
     genetic
    0.41
     inherit
    0.40
    her
    0.39
     Genetic
    0.38
     Genetics
    0.37
     Her
    0.36
     inheritance
    0.36
    Activations Density 0.039%

    No Known Activations