© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 41811
    Prev
    Next
    INDEX
    Explanations

    references to medical diagnoses and the challenges associated with them

    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
    одо
    -0.14
    reon
    -0.14
    insky
    -0.14
    ÑģÑĤеÑĢ
    -0.14
    ãĥ¼ãĥĸ
    -0.14
    dre
    -0.14
    ieve
    -0.13
    ยà¸Ļ
    -0.13
     Ø¢ÙĪرد
    -0.13
    IRT
    -0.13
    POSITIVE LOGITS
    di
    0.89
     Di
    0.89
    -di
    0.85
    Di
    0.81
     di
    0.79
     diag
    0.74
    _di
    0.74
     diagnosis
    0.73
     diagnose
    0.69
    .di
    0.68
    Activations Density 0.016%

    No Known Activations