© 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. 32949
    Prev
    Next
    INDEX
    Explanations

    terms related to advancements and applications in medical technology and research

    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
    ento
    -0.15
    eties
    -0.14
    hof
    -0.14
    osis
    -0.13
    /world
    -0.13
    à¸ļà¸Ļ
    -0.13
    ÑģÑĤÑĢ
    -0.13
    zier
    -0.13
    zel
    -0.13
    emouth
    -0.13
    POSITIVE LOGITS
     field
    0.75
     fields
    0.75
    field
    0.59
     Fields
    0.58
     Field
    0.58
    fields
    0.56
    -field
    0.54
     FIELD
    0.53
    Field
    0.53
    _field
    0.52
    Activations Density 0.117%

    No Known Activations