© 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. 61659
    Prev
    Next
    INDEX
    Explanations

    superficiality and condescension

    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
    sexy
    -0.10
     lekker
    -0.09
     rel
    -0.09
    füh
    -0.08
     austerity
    -0.08
    adam
    -0.08
    rim
    -0.08
    939
    -0.08
     fucked
    -0.08
    arching
    -0.08
    POSITIVE LOGITS
     shallow
    0.27
    æµħ
    0.19
     artificial
    0.18
     tack
    0.18
     superficial
    0.15
     pand
    0.15
     повеÑĢÑħ
    0.15
    ä¿Ĺ
    0.15
     empty
    0.14
     hollow
    0.14
    Activations Density 0.137%

    No Known Activations