© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 24193
    Prev
    Next
    INDEX
    Explanations

    instances of the pronoun "I" indicating a personal perspective or emphasis

    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
     reck
    -0.16
    t
    -0.15
    l
    -0.15
     terr
    -0.15
    m
    -0.14
    las
    -0.14
    μη
    -0.13
    CLE
    -0.13
    f
    -0.13
    _imag
    -0.13
    POSITIVE LOGITS
    elts
    0.19
     hope
    0.16
     am
    0.16
    ï¸ı
    0.16
    ábado
    0.15
    /flutter
    0.15
    ront
    0.15
    ’m
    0.15
    rides
    0.15
    spor
    0.15
    Activations Density 0.110%

    No Known Activations