© 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. 53976
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" and their various usages in context

    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
    Ư
    -0.15
    UNDLE
    -0.15
     INCIDENT
    -0.14
    é¤Ĭ
    -0.14
    <decltype
    -0.14
    ennen
    -0.14
    enson
    -0.13
     INTERRU
    -0.13
     ragaz
    -0.13
    üh
    -0.13
    POSITIVE LOGITS
     a
    0.35
     an
    0.29
    ä¸Ģ个
    0.23
     lots
    0.22
    :
    0.21
     eine
    0.20
    —a
    0.20
     sebuah
    0.20
    a
    0.19
     another
    0.18
    Activations Density 0.094%

    No Known Activations