© 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. 41342
    Prev
    Next
    INDEX
    Explanations

    themes related to political dissent and authoritarianism

    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
    arih
    -0.15
    holm
    -0.15
     Fol
    -0.15
     abandonment
    -0.14
    ëĦ·
    -0.13
    actal
    -0.13
     Puerto
    -0.13
     heightFor
    -0.13
    ndl
    -0.12
    à¹īาà¸Ĭ
    -0.12
    POSITIVE LOGITS
     regime
    0.31
     censorship
    0.27
     underground
    0.26
     restricted
    0.24
     repression
    0.23
     freedom
    0.23
     režim
    0.23
     restrictions
    0.23
     censor
    0.22
     officially
    0.21
    Activations Density 0.036%

    No Known Activations