© 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. 29026
    Prev
    Next
    INDEX
    Explanations

    terms related to classification and existence

    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
    _Two
    -0.14
     -*-č↵
    -0.14
    hores
    -0.14
    Three
    -0.13
    filer
    -0.13
    eview
    -0.13
    Two
    -0.13
    ulması
    -0.12
    uned
    -0.12
    หมà¸Ķ
    -0.12
    POSITIVE LOGITS
     one
    1.10
     ÛĮÚ©ÛĮ
    0.66
     eines
    0.64
     uno
    0.63
     salah
    0.62
    ä¹ĭä¸Ģ
    0.61
    one
    0.57
     одного
    0.54
    _one
    0.54
     одним
    0.52
    Activations Density 0.136%

    No Known Activations