© 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. 33093
    Prev
    Next
    INDEX
    Explanations

    phrases indicating inactivity or passivity

    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
    ioneer
    -0.15
    ÏĮ
    -0.15
    osate
    -0.15
    linger
    -0.14
    ahi
    -0.14
     discreet
    -0.14
     slightly
    -0.14
    moz
    -0.14
    alion
    -0.14
     preferredStyle
    -0.14
    POSITIVE LOGITS
     id
    0.31
     sidelines
    0.23
    (id
    0.21
    .id
    0.21
    -id
    0.20
     passive
    0.20
     idle
    0.20
     tw
    0.19
    	id
    0.19
    /id
    0.18
    Activations Density 0.024%

    No Known Activations