© 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. 3350
    Prev
    Next
    INDEX
    Explanations

    furry, Japanese, and meme subcultures

    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
     Rum
    -0.10
     Carbon
    -0.09
    æ·»
    -0.09
    ennes
    -0.09
     sut
    -0.09
     subsidized
    -0.08
    lass
    -0.08
     é¦
    -0.08
     google
    -0.08
    loff
    -0.08
    POSITIVE LOGITS
     culture
    0.22
     underground
    0.21
     cultures
    0.18
     Culture
    0.18
    culture
    0.18
     communities
    0.17
     sub
    0.16
    Culture
    0.16
    ulture
    0.14
    åľ°ä¸ĭ
    0.14
    Activations Density 0.176%

    No Known Activations