© 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. 24390
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and expressions of personal perspective or experience

    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
    айд
    -0.15
    ettle
    -0.14
    iker
    -0.14
    obre
    -0.14
    ugins
    -0.14
    leta
    -0.14
    likes
    -0.14
    ickname
    -0.14
     fond
    -0.14
     accomplish
    -0.13
    POSITIVE LOGITS
     can
    0.24
    can
    0.20
    'm
    0.19
    ’m
    0.18
     am
    0.18
    QS
    0.17
     worry
    0.16
    .can
    0.16
     worries
    0.15
     certainly
    0.15
    Activations Density 0.068%

    No Known Activations