© 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. 23890
    Prev
    Next
    INDEX
    Explanations

    terms related to medical monitoring and patient care

    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
    ousse
    -0.16
     thaw
    -0.16
    olik
    -0.16
    øj
    -0.14
    lisi
    -0.14
    ãģķãĤī
    -0.14
    ẩn
    -0.14
    EMPL
    -0.14
    aines
    -0.14
     Serg
    -0.14
    POSITIVE LOGITS
     oxygen
    0.49
     Oxygen
    0.47
     breathing
    0.46
     breathed
    0.41
     breathe
    0.41
     respiratory
    0.40
     breath
    0.39
     lungs
    0.38
     respir
    0.37
     Respir
    0.36
    Activations Density 0.024%

    No Known Activations