© 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. 15586
    Prev
    Next
    INDEX
    Explanations

    phrases related to uncertainty and missing data representation

    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
     Vernon
    -0.13
    .LayoutStyle
    -0.13
    ÏĮγ
    -0.12
    å·
    -0.12
    öyle
    -0.12
    ä¸Ģåį·
    -0.11
    uan
    -0.11
    ignon
    -0.11
    fromJson
    -0.11
    rowable
    -0.11
    POSITIVE LOGITS
     value
    1.14
    value
    0.93
     Value
    0.93
     values
    0.92
    -value
    0.86
    åĢ¼
    0.84
    Value
    0.84
    _value
    0.81
     VALUE
    0.81
     Values
    0.79
    Activations Density 0.021%

    No Known Activations