© 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. 35787
    Prev
    Next
    INDEX
    Explanations

    slang and colloquial expressions

    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
     syll
    -0.10
     gramm
    -0.10
     trous
    -0.10
     Afr
    -0.09
     renamed
    -0.09
    arend
    -0.09
     ÙĪصÙĦ
    -0.08
     Sony
    -0.08
     textual
    -0.08
     Bul
    -0.08
    POSITIVE LOGITS
     idi
    0.21
     slang
    0.20
     expressions
    0.20
     жаÑĢ
    0.19
     informal
    0.19
    idi
    0.18
     expression
    0.18
     arg
    0.18
     dialect
    0.18
    ä¿Ĺ
    0.17
    Activations Density 0.267%

    No Known Activations