© 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. 33569
    Prev
    Next
    INDEX
    Explanations

    statements that refute common misconceptions

    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
     THAT
    -0.35
    éĤ£ä¸ª
    -0.33
     Äijó
    -0.33
     That
    -0.32
    éĤ£ç§į
    -0.32
    That
    -0.30
     Ø°ÙĦÙĥ
    -0.30
     quella
    -0.30
     that
    -0.30
    éĤ£æł·
    -0.28
    POSITIVE LOGITS
     these
    0.86
    these
    0.75
     These
    0.73
    These
    0.71
     THESE
    0.69
    è¿ĻäºĽ
    0.65
     estos
    0.53
     ÑįÑĤиÑħ
    0.53
     ÑĨиÑħ
    0.49
    "These
    0.48
    Activations Density 0.015%

    No Known Activations