© 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. 29134
    Prev
    Next
    INDEX
    Explanations

    phrases related to authority and power dynamics

    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
    ivas
    -0.17
    äl
    -0.16
    หลาย
    -0.16
    many
    -0.15
     numerous
    -0.15
     many
    -0.15
    ilet
    -0.15
     vielen
    -0.14
     Wass
    -0.14
    inx
    -0.14
    POSITIVE LOGITS
     lots
    0.25
     considerable
    0.23
     Lots
    0.23
    Lots
    0.22
     plenty
    0.21
    lots
    0.20
     alot
    0.19
     tremendous
    0.19
     some
    0.18
     immense
    0.17
    Activations Density 0.039%

    No Known Activations