© 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. 24055
    Prev
    Next
    INDEX
    Explanations

    phrases related to authority and governance issues

    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
     either
    -0.45
     Either
    -0.44
    Either
    -0.40
    either
    -0.39
     EITHER
    -0.35
     soit
    -0.18
    isoft
    -0.18
     либо
    -0.17
    ichever
    -0.16
    ç©´
    -0.15
    POSITIVE LOGITS
     nor
    1.17
    nor
    0.81
     Nor
    0.77
    Nor
    0.71
     NOR
    0.68
     neither
    0.39
     nors
    0.39
     Norris
    0.35
     né
    0.33
     ноÑĢ
    0.33
    Activations Density 0.014%

    No Known Activations