© 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. 9563
    Prev
    Next
    INDEX
    Explanations

    Dutch phrase or derogatory term

    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
     vowels
    -0.13
     Pron
    -0.13
     synonyms
    -0.12
     pronunciation
    -0.12
     vowel
    -0.11
    åŃĹ
    -0.10
     surname
    -0.10
     nouns
    -0.10
     spelling
    -0.10
     syll
    -0.10
    POSITIVE LOGITS
     phrase
    0.57
     expression
    0.51
    phrase
    0.43
     Phrase
    0.42
     expressions
    0.42
     phrases
    0.41
    expression
    0.41
     Expression
    0.39
    Phrase
    0.38
    Expression
    0.36
    Activations Density 0.282%

    No Known Activations