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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 33005
    Prev
    Next
    INDEX
    Explanations

    references to personal choices and reproductive rights

    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
    ÑģÑĤвоÑĢ
    -0.17
    awei
    -0.16
    hung
    -0.16
    oma
    -0.15
    oji
    -0.15
    ampo
    -0.15
    zeigen
    -0.14
     PROFITS
    -0.14
    logy
    -0.14
     politics
    -0.13
    POSITIVE LOGITS
     choices
    0.34
     life
    0.29
     Choices
    0.28
    choices
    0.26
     lifestyle
    0.26
     Life
    0.25
    Life
    0.23
     CHO
    0.23
    life
    0.23
     cho
    0.21
    Activations Density 0.024%

    No Known Activations