© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 63118
    Prev
    Next
    INDEX
    Explanations

    "then" or "allow" or "make" followed by "they" or "them"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hers
    -0.22
     ours
    -0.14
     deren
    -0.10
     onun
    -0.10
     yours
    -0.09
     Onun
    -0.09
    apos
    -0.09
     onu
    -0.09
    isini
    -0.09
    ladım
    -0.09
    POSITIVE LOGITS
     they
    0.61
     They
    0.50
    they
    0.49
    They
    0.48
     mereka
    0.48
     há»į
    0.47
     они
    0.45
    ä»ĸ们
    0.45
    ä»ĸåĢij
    0.37
    ï¼Įä»ĸ们
    0.36
    Activations Density 0.248%

    No Known Activations