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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 63371
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "be" and related expressions of existence or presence

    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
     ÅĻÃŃj
    -0.17
    being
    -0.17
    okud
    -0.16
     bÅĻez
    -0.16
    /XML
    -0.14
    akah
    -0.14
    اÙĨÙĩ
    -0.14
    nr
    -0.14
     siendo
    -0.13
    skyt
    -0.13
    POSITIVE LOGITS
     no
    0.29
     a
    0.25
     some
    0.24
     another
    0.23
     an
    0.22
     times
    0.21
     room
    0.20
     many
    0.20
     fewer
    0.20
     more
    0.18
    Activations Density 0.076%

    No Known Activations