© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 13756
    Prev
    Next
    INDEX
    Explanations

    may, might, can, could, possible

    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
    cant
    -0.10
     Cannot
    -0.09
     Cant
    -0.09
    maktan
    -0.08
     devez
    -0.08
     cant
    -0.08
    YPES
    -0.08
    makt
    -0.08
    osi
    -0.08
    Cannot
    -0.08
    POSITIVE LOGITS
     could
    0.58
     might
    0.48
     may
    0.44
    could
    0.44
     olabilir
    0.43
     bisa
    0.41
     puede
    0.41
     सà¤ķत
    0.39
     poate
    0.38
     może
    0.38
    Activations Density 0.306%

    No Known Activations