© 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. 40827
    Prev
    Next
    INDEX
    Explanations

    references to misconduct and violations of policies or laws

    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
    PTR
    -0.14
    íı´
    -0.13
    423
    -0.13
    uja
    -0.13
     Pont
    -0.13
    ptom
    -0.13
    ượng
    -0.13
    /portfolio
    -0.12
    sworth
    -0.12
    orio
    -0.12
    POSITIVE LOGITS
     pay
    1.14
     Pay
    1.03
     paid
    0.99
    pay
    0.96
    Pay
    0.94
     paying
    0.94
     pays
    0.91
     PAY
    0.90
    -pay
    0.87
     Payne
    0.85
    Activations Density 0.006%

    No Known Activations