© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 1363
    Prev
    Next
    INDEX
    Explanations

    idioma español. Aqu

    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
     Lingu
    -0.11
     lingu
    -0.11
    ingu
    -0.10
     translators
    -0.10
     linguistic
    -0.09
     Colomb
    -0.09
     asian
    -0.09
     indian
    -0.09
    uku
    -0.09
     Alfred
    -0.09
    POSITIVE LOGITS
     English
    0.30
    English
    0.24
     languages
    0.22
    èĭ±è¯Ń
    0.21
     english
    0.20
     language
    0.20
    à¸łà¸²à¸©
    0.19
    èĭ±èªŀ
    0.19
     tiếng
    0.19
     Spanish
    0.17
    Activations Density 0.225%

    No Known Activations