© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 27886
    Prev
    Next
    INDEX
    Explanations

    language spoken or official

    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
    Negative Logits
     bilingual
    -0.14
     pron
    -0.12
     linguistic
    -0.11
     pronunciation
    -0.10
    pron
    -0.10
     Pron
    -0.10
     Sikh
    -0.10
     lingu
    -0.09
    elib
    -0.09
     primitive
    -0.09
    POSITIVE LOGITS
     spoken
    0.23
     official
    0.20
    spoken
    0.18
     spoke
    0.17
     Official
    0.16
    official
    0.15
     speakers
    0.15
    å®ĺæĸ¹
    0.15
     å®ĺ
    0.15
     veh
    0.14
    Activations Density 0.095%

    No Known Activations