© 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. 24159
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation or conjunctions that indicate a contrast or continuation in thought

    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
     each
    -0.18
     there
    -0.17
    there
    -0.16
    each
    -0.15
     people
    -0.14
    erva
    -0.13
     various
    -0.13
    ceiver
    -0.13
     everything
    -0.13
     à¤īसन
    -0.12
    POSITIVE LOGITS
     their
    0.49
     Their
    0.47
    Their
    0.46
     they
    0.45
     THEY
    0.45
     They
    0.45
    They
    0.44
    ä»ĸ们
    0.44
     THEIR
    0.44
    their
    0.43
    Activations Density 0.032%

    No Known Activations