© 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. 41006
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to time and scheduling

    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
    StringRef
    -0.16
    ormsg
    -0.16
     everywhere
    -0.15
    èĶµ
    -0.15
    chedulers
    -0.15
    StandardItem
    -0.14
    ằng
    -0.13
    atories
    -0.13
    DownList
    -0.12
    lah
    -0.12
    POSITIVE LOGITS
     select
    1.08
     selected
    0.98
    selected
    0.83
     Selected
    0.82
    select
    0.79
    Selected
    0.75
     Select
    0.75
    -selected
    0.72
    Select
    0.71
     SELECT
    0.71
    Activations Density 0.018%

    No Known Activations