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

    Neuronpedia

    Jacobian LensNEW
    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. 42610
    Prev
    Next
    INDEX
    Explanations

    expressions related to personal identity and autonomy

    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
    ë³
    -0.18
    rost
    -0.17
     reput
    -0.17
    esser
    -0.14
     ÙħستÙĤ
    -0.14
    -li
    -0.14
     Reputation
    -0.14
    amburger
    -0.14
    poss
    -0.14
    å¼ķãģį
    -0.14
    POSITIVE LOGITS
     opinions
    0.32
     thoughts
    0.30
     opinion
    0.30
     views
    0.25
     Thoughts
    0.24
     Opinion
    0.23
     pent
    0.22
     ideas
    0.22
     sentiments
    0.21
     feelings
    0.21
    Activations Density 0.031%

    No Known Activations