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. 23730
    Prev
    Next
    INDEX
    Explanations

    occurrences of the pronoun "I" and related phrases indicating personal opinion or reflection

    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
    .contacts
    -0.15
    erne
    -0.15
     desn
    -0.15
    fak
    -0.15
     Stateless
    -0.14
    kü
    -0.14
    íĶĪ
    -0.14
    theid
    -0.14
     Mention
    -0.14
     Recomm
    -0.14
    POSITIVE LOGITS
     thought
    0.20
     hast
    0.19
     kid
    0.18
     mean
    0.17
     tell
    0.17
     suppose
    0.16
     reasoning
    0.16
     tells
    0.15
    batis
    0.15
     reflection
    0.15
    Activations Density 0.036%

    No Known Activations