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. 23633
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and memories

    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
    linger
    -0.16
    ÙĪØ§Ø±Ùĩ
    -0.15
     Daughter
    -0.14
    ÄIJT
    -0.13
    ÑĢÑĮ
    -0.13
    ault
    -0.13
     oran
    -0.13
     delim
    -0.13
     Welch
    -0.13
    вÑĸлÑĮ
    -0.13
    POSITIVE LOGITS
     was
    0.28
     first
    0.23
    first
    0.20
    was
    0.19
    .first
    0.18
     бÑĭл
    0.18
     byÅĤo
    0.18
     бÑĭло
    0.17
     byÅĤ
    0.17
     était
    0.17
    Activations Density 0.045%

    No Known Activations