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

    Neuronpedia

    Jacobian LensNEW
    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. 14591
    Prev
    Next
    INDEX
    Explanations

    occurrences of commas and phrases indicating irony or surprise

    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
    ãģĸ
    -0.15
    yas
    -0.14
    (æľ¨
    -0.14
    .now
    -0.14
    agne
    -0.14
     οÏĢοίο
    -0.13
    illet
    -0.13
    اذا
    -0.13
    estre
    -0.13
    inth
    -0.13
    POSITIVE LOGITS
     however
    0.36
     this
    0.32
     none
    0.29
     though
    0.26
     neither
    0.24
    however
    0.24
     these
    0.24
    these
    0.23
    none
    0.23
     NONE
    0.22
    Activations Density 0.130%

    No Known Activations