© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 58870
    Prev
    Next
    INDEX
    Explanations

    clarification on pronunciation

    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
     slang
    -0.11
     bilingual
    -0.11
     grams
    -0.11
     Gram
    -0.10
     verb
    -0.10
     Verb
    -0.09
    Gram
    -0.09
     compos
    -0.09
    aders
    -0.09
    ament
    -0.09
    POSITIVE LOGITS
     sounds
    0.21
     IPA
    0.19
    IPA
    0.18
     пÑĢоиз
    0.17
     Sounds
    0.16
     à¤īà¤ļ
    0.16
     accent
    0.16
     تÙĦÙģ
    0.15
     transcription
    0.15
     sound
    0.15
    Activations Density 0.095%

    No Known Activations