© 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. 21109
    Prev
    Next
    INDEX
    Explanations

    explaining pronunciation rules

    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
    -0.14
     verb
    -0.14
     synonyms
    -0.14
     synonym
    -0.12
     Verb
    -0.12
     primitive
    -0.12
    ocab
    -0.11
     collo
    -0.10
     verbs
    -0.10
    primitive
    -0.10
    POSITIVE LOGITS
     transl
    0.16
     cogn
    0.15
     Romance
    0.15
     loan
    0.12
     endings
    0.11
     sounded
    0.11
    illow
    0.11
    éŁ³
    0.11
     ÑĤÑĢан
    0.10
     transcription
    0.10
    Activations Density 0.103%

    No Known Activations