© 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. 54360
    Prev
    Next
    INDEX
    Explanations

    concepts related to the complexity and variation in brain illnesses and the limitations of uniformity in understanding 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
     Separate
    -0.13
    ucher
    -0.13
    ÑİÑĢ
    -0.13
     combination
    -0.13
    ạm
    -0.13
    à¹Ģà¸Ł
    -0.13
    à¹Ĥà¸ķ
    -0.13
     Combo
    -0.13
    .appspot
    -0.13
     asymmetric
    -0.13
    POSITIVE LOGITS
     uniform
    0.77
    uniform
    0.61
     Uniform
    0.60
    Uniform
    0.59
     hom
    0.51
     unified
    0.50
    _uniform
    0.48
     homogeneous
    0.47
     uniformly
    0.45
    .uniform
    0.45
    Activations Density 0.033%

    No Known Activations