© 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. 41302
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and their characteristics or complications

    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
     rough
    -0.15
    /raw
    -0.14
    foy
    -0.14
    	typedef
    -0.14
     hear
    -0.14
     saw
    -0.13
     Hayward
    -0.13
    аÑİÑĤ
    -0.13
     soon
    -0.13
    Ñĭва
    -0.13
    POSITIVE LOGITS
     understood
    0.37
     known
    0.36
     established
    0.35
     well
    0.34
    -known
    0.33
    known
    0.32
    -established
    0.30
     Known
    0.29
    well
    0.28
     Ø´ÙĨاختÙĩ
    0.28
    Activations Density 0.042%

    No Known Activations