© 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. 42914
    Prev
    Next
    INDEX
    Explanations

    modal verbs and phrases indicating possibility 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
    ãģ«ãģ¦
    -0.16
    èĥ½å¤Ł
    -0.14
     Purchase
    -0.13
    kır
    -0.13
    ÑģÑı
    -0.13
    å°ĩ
    -0.13
     physicians
    -0.13
    htmlspecialchars
    -0.13
     Individuals
    -0.13
     occurring
    -0.12
    POSITIVE LOGITS
    æ¡Ī
    0.14
    odeled
    0.13
     partly
    0.13
    ogene
    0.13
    -chevron
    0.13
    anga
    0.13
     ***!↵
    0.13
    ague
    0.13
    ispers
    0.13
    movies
    0.13
    Activations Density 0.020%

    No Known Activations