© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 28355
    Prev
    Next
    INDEX
    Explanations

    expressions related to hesitation or uncertainty

    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
    ede
    -0.13
    '|
    -0.12
    ÑĩÑĥк
    -0.12
    lena
    -0.12
     Ãĸn
    -0.12
    eniable
    -0.12
    reload
    -0.12
    lds
    -0.12
    ̣
    -0.12
    anki
    -0.12
    POSITIVE LOGITS
     to
    0.51
    	to
    0.26
     tp
    0.24
    to
    0.23
     toItem
    0.21
     να
    0.20
     Äijá»ĥ
    0.19
    ãĤĴ
    0.19
     zu
    0.18
    ToAdd
    0.18
    Activations Density 0.663%

    No Known Activations