© 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. 30320
    Prev
    Next
    INDEX
    Explanations

    references to significant quantities or impactful events

    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
     indeb
    -0.16
     closest
    -0.13
     nearest
    -0.13
    afort
    -0.13
    ãģ¾ãģļ
    -0.13
     trÆ°á»Łng
    -0.12
    zza
    -0.12
    atas
    -0.12
    ıb
    -0.12
     triples
    -0.12
    POSITIVE LOGITS
     second
    1.36
    second
    1.15
    Second
    0.97
    第äºĮ
    0.97
     SECOND
    0.95
     Second
    0.95
    -second
    0.94
    .second
    0.89
     Secondly
    0.86
     第äºĮ
    0.86
    Activations Density 0.052%

    No Known Activations