© 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. 46513
    Prev
    Next
    INDEX
    Explanations

    Spanish initial question marks and end punctuation

    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
    -0.11
    Mais
    -0.10
     automáticamente
    -0.10
    EEP
    -0.10
    olist
    -0.10
    iedade
    -0.10
     sigu
    -0.10
     na
    -0.10
     pass
    -0.10
     Mais
    -0.10
    POSITIVE LOGITS
     ¿
    0.20
    ¿
    0.17
     dime
    0.12
     nuest
    0.12
     lo
    0.11
     sea
    0.11
     pract
    0.11
     ¡
    0.10
     Incre
    0.10
     voy
    0.10
    Activations Density 0.299%

    No Known Activations