© 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. 40929
    Prev
    Next
    INDEX
    Explanations

    articles and demonstratives preceding nouns

    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
     ëĦ¤ìĿ´íĬ¸
    -0.16
     ëĭ¤ìļ´ë°Ľê¸°
    -0.13
    ë¨
    -0.13
     ëħĦëıĦë³Ħ
    -0.13
    orst
    -0.13
    ëĿ¼íͼ
    -0.13
    надлеж
    -0.13
    .CustomButton
    -0.12
     зави
    -0.12
    æļ
    -0.12
    POSITIVE LOGITS
     following
    0.23
     above
    0.22
     same
    0.19
     last
    0.18
    ses
    0.18
    ese
    0.18
     whole
    0.17
     next
    0.17
     rest
    0.17
     entire
    0.16
    Activations Density 0.254%

    No Known Activations