© 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. 24528
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter "H" in relation to healthcare terminology and contexts

    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
    dek
    -0.17
    idden
    -0.17
    ash
    -0.16
    imb
    -0.16
    andles
    -0.16
    ASH
    -0.16
    orny
    -0.16
    UD
    -0.15
    ave
    -0.15
    entai
    -0.15
    POSITIVE LOGITS
    esco
    0.17
    tin
    0.17
    rz
    0.16
    rst
    0.16
    cı
    0.16
     pyl
    0.16
    rana
    0.16
    avaÅŁ
    0.16
    ively
    0.15
    r
    0.15
    Activations Density 0.029%

    No Known Activations