© 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. 14073
    Prev
    Next
    INDEX
    Explanations

    references to government actions and criticism

    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
     üzere
    -0.17
    pez
    -0.16
    ole
    -0.16
    ansa
    -0.16
    ores
    -0.14
    ein
    -0.14
    ges
    -0.13
    fak
    -0.13
    elin
    -0.13
    iez
    -0.13
    POSITIVE LOGITS
     government
    0.69
     Government
    0.54
    government
    0.54
    æĶ¿åºľ
    0.51
     governments
    0.50
    Government
    0.48
    -government
    0.45
     governo
    0.44
     gobierno
    0.43
     सरà¤ķ
    0.40
    Activations Density 0.118%

    No Known Activations