© 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. 15126
    Prev
    Next
    INDEX
    Explanations

    the word "Aside" as it indicates a shift in topic or commentary

    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
    lass
    -0.17
    las
    -0.16
    ToWorld
    -0.16
    reh
    -0.15
    erton
    -0.15
    ави
    -0.14
    Ñĥз
    -0.14
    lah
    -0.13
    lis
    -0.13
    inho
    -0.13
    POSITIVE LOGITS
     from
    0.38
    from
    0.30
     FROM
    0.26
     från
    0.25
    	from
    0.25
    à¸Īาà¸ģà¸ģาร
    0.24
     dari
    0.23
    .from
    0.23
     From
    0.23
    à¸Īาà¸ģ
    0.23
    Activations Density 0.013%

    No Known Activations