© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8581
    Prev
    Next
    INDEX
    Explanations

    phrases that reference vigilance or scrutiny

    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
    Ñĥнк
    -0.15
    urator
    -0.15
    imir
    -0.15
    epar
    -0.15
    witter
    -0.14
    din
    -0.14
    isay
    -0.14
    imore
    -0.14
    opa
    -0.14
    Æł
    -0.14
    POSITIVE LOGITS
     on
    0.27
     fixed
    0.22
     peeled
    0.20
     trained
    0.19
    trained
    0.17
     open
    0.16
     Fixed
    0.16
    fixed
    0.16
     focused
    0.15
     на
    0.15
    Activations Density 0.024%

    No Known Activations