© 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. 21079
    Prev
    Next
    INDEX
    Explanations

    language differences and origins

    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
    -0.14
     linguistic
    -0.11
     Lingu
    -0.11
     fluent
    -0.10
     languages
    -0.10
     language
    -0.10
     Verb
    -0.10
    _languages
    -0.10
    063
    -0.10
     gramm
    -0.09
    POSITIVE LOGITS
     spell
    0.14
     Standard
    0.14
     loan
    0.14
     Speakers
    0.14
     speakers
    0.13
    åĢŁ
    0.12
     influences
    0.12
     Loan
    0.12
    endon
    0.12
     Orth
    0.12
    Activations Density 0.101%

    No Known Activations