© 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. 24490
    Prev
    Next
    INDEX
    Explanations

    punctuation and phrases indicating direct speech or quotations

    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
    uitka
    -0.17
     lại
    -0.16
    _firestore
    -0.15
    âĹİ
    -0.14
    ĵĺ
    -0.14
     handjob
    -0.13
    matchCondition
    -0.13
    agree
    -0.13
    styleType
    -0.13
    IDDEN
    -0.13
    POSITIVE LOGITS
     read
    0.23
     etc
    0.19
     reads
    0.17
    reads
    0.17
    read
    0.17
    elay
    0.16
    /read
    0.16
    iddle
    0.16
     we
    0.15
     declared
    0.15
    Activations Density 0.046%

    No Known Activations