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. 23184
    Prev
    Next
    INDEX
    Explanations

    instances of social media activity and engagement

    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
    akov
    -0.18
     íĬ¹ë³Ħ
    -0.15
    hib
    -0.15
    è¢ĸ
    -0.14
    ìŀij
    -0.14
    Mailer
    -0.14
    /browse
    -0.14
     CrossRef
    -0.14
    Xã
    -0.14
    ohon
    -0.14
    POSITIVE LOGITS
     links
    0.33
     link
    0.29
     pictures
    0.28
     photos
    0.26
    -links
    0.24
    links
    0.23
     Links
    0.23
     Link
    0.22
     picture
    0.22
    Links
    0.21
    Activations Density 0.080%

    No Known Activations