© 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. 22857
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparisons or distinctions between different states or conditions

    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
    tti
    -0.15
    à¹īาร
    -0.14
    zb
    -0.14
    oller
    -0.14
    ymous
    -0.14
    avra
    -0.14
    룴
    -0.14
    .Creator
    -0.14
     incap
    -0.13
    olla
    -0.13
    POSITIVE LOGITS
     bad
    1.05
     Bad
    0.94
    bad
    0.88
    Bad
    0.87
     BAD
    0.86
    _bad
    0.71
    BAD
    0.70
    .bad
    0.66
    .Bad
    0.64
    _BAD
    0.57
    Activations Density 0.031%

    No Known Activations