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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 39
    Prev
    Next
    INDEX
    Explanations

    instances of the pronoun "I" and related expressions of personal opinion or experiences

    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
    igne
    -0.17
    OTO
    -0.14
    æĹ
    -0.14
    (DWORD
    -0.14
    ẫn
    -0.14
    ست
    -0.13
    dar
    -0.13
    nier
    -0.13
    tml
    -0.13
    amespace
    -0.13
    POSITIVE LOGITS
     imp
    0.20
     personally
    0.19
     belief
    0.18
     Personally
    0.17
     for
    0.17
     sure
    0.16
     hope
    0.16
     believe
    0.16
    -bel
    0.15
     truly
    0.15
    Activations Density 0.064%

    No Known Activations