© 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. 16508
    Prev
    Next
    INDEX
    Explanations

    Brazilian Portuguese tourism and classroom

    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
     nuest
    -0.22
     follando
    -0.18
     pione
    -0.15
     grátis
    -0.14
    _numero
    -0.13
     ragaz
    -0.13
     acompanh
    -0.12
     acompan
    -0.12
    Telefono
    -0.11
    ición
    -0.11
    POSITIVE LOGITS
     Brazilian
    0.16
     Portuguese
    0.15
     Rede
    0.14
     tô
    0.14
    º
    0.13
     plata
    0.13
    inha
    0.13
    ão
    0.12
    empre
    0.12
     quil
    0.12
    Activations Density 0.314%

    No Known Activations