© 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. 4723
    Prev
    Next
    INDEX
    Explanations

    y seguido de 'of' o 'para'

    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
     desar
    -0.13
     acomp
    -0.13
     frequent
    -0.12
     automáticamente
    -0.12
     difÃŃc
    -0.11
     generado
    -0.11
    .Classes
    -0.10
     adequ
    -0.10
     frequ
    -0.10
     intimate
    -0.10
    POSITIVE LOGITS
     teste
    0.12
     considerable
    0.12
     y
    0.11
    aciones
    0.10
    ologÃŃa
    0.10
     ende
    0.10
     ¡
    0.10
     ya
    0.10
     excav
    0.09
     Tales
    0.09
    Activations Density 0.258%

    No Known Activations