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. 31414
    Prev
    Next
    INDEX
    Explanations

    phrases related to instructions or guidance

    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
    IODevice
    -0.17
    ibs
    -0.15
     accordingly
    -0.14
    RequestMethod
    -0.13
    udies
    -0.13
    pect
    -0.13
    ignum
    -0.13
    olit
    -0.13
    ugins
    -0.13
    utdown
    -0.13
    POSITIVE LOGITS
     panorama
    0.18
     yr
    0.17
     finest
    0.16
    .th
    0.16
     hyperlink
    0.16
     weblog
    0.16
     https
    0.16
     comfy
    0.16
     outcomes
    0.15
     benefici
    0.15
    Activations Density 0.045%

    No Known Activations