© 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. 15676
    Prev
    Next
    INDEX
    Explanations

    references to political views and shifts, particularly regarding social issues like marriage

    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
    èıĮ
    -0.17
     Beard
    -0.14
    ekce
    -0.14
    powers
    -0.14
    AppState
    -0.14
    decoded
    -0.13
     Roses
    -0.13
    ibold
    -0.13
     丶
    -0.13
    à¸Ľà¸ı
    -0.13
    POSITIVE LOGITS
     changed
    0.33
     changing
    0.31
     change
    0.30
     Changed
    0.28
    changing
    0.27
     Changing
    0.27
    changed
    0.27
    -changing
    0.26
    Changed
    0.26
    Changing
    0.26
    Activations Density 0.028%

    No Known Activations