© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 42346
    Prev
    Next
    INDEX
    Explanations

    attributes and characteristics of plant leaves

    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
    erin
    -0.15
    erton
    -0.14
     jams
    -0.14
    zh
    -0.14
    annis
    -0.14
    ewan
    -0.14
     Column
    -0.14
    imus
    -0.14
    ftar
    -0.14
     concrete
    -0.14
    POSITIVE LOGITS
     leaves
    0.54
     leaf
    0.51
     Leaves
    0.49
     Leaf
    0.45
    Leaf
    0.45
    leaf
    0.45
    åı¶
    0.41
    èijī
    0.35
     leave
    0.34
    _leaf
    0.33
    Activations Density 0.012%

    No Known Activations