© 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. 10080
    Prev
    Next
    INDEX
    Explanations

    account, brand, query, application, letter

    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
     stesso
    -0.16
     electrónico
    -0.15
     completo
    -0.14
     himself
    -0.14
     italiano
    -0.12
     público
    -0.12
     gratuito
    -0.11
     اÙĦØ£ÙħرÙĬÙĥÙĬ
    -0.11
     اÙĦÙĪØ·ÙĨÙĬ
    -0.11
     français
    -0.11
    POSITIVE LOGITS
     herself
    0.19
     italiana
    0.16
     à¤Ĩà¤Ī
    0.12
    ública
    0.12
     latina
    0.12
     ÑĤакаÑı
    0.12
     коÑĤоÑĢаÑı
    0.12
     pública
    0.12
     бÑĭла
    0.12
    ção
    0.11
    Activations Density 0.268%

    No Known Activations