Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 23701
    Prev
    Next
    INDEX
    Explanations

    instances of the word "that" used in various grammatical contexts

    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
    ä¹ĭä¸Ģ
    -0.17
    iler
    -0.15
    ÐĴС
    -0.15
    ewise
    -0.14
    .VisualBasic
    -0.14
    æºIJ
    -0.14
     why
    -0.14
    enticated
    -0.14
    dül
    -0.14
     offsetof
    -0.14
    POSITIVE LOGITS
     alone
    0.25
     Alone
    0.19
     itself
    0.18
    alone
    0.18
     unto
    0.16
    hani
    0.15
    agli
    0.14
     kind
    0.14
     sola
    0.14
     scenario
    0.14
    Activations Density 0.034%

    No Known Activations