© 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. 62666
    Prev
    Next
    INDEX
    Explanations

    writing quality components

    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
     languages
    -0.18
     linguistic
    -0.17
     Languages
    -0.17
     Language
    -0.16
     Lingu
    -0.16
     lingu
    -0.15
     language
    -0.15
    Languages
    -0.14
    Language
    -0.14
     ngôn
    -0.14
    POSITIVE LOGITS
     style
    0.11
    éĢ
    0.10
     Tato
    0.10
     punctuation
    0.10
     overall
    0.10
     tense
    0.10
    ilib
    0.10
     logic
    0.10
     Style
    0.09
     spell
    0.09
    Activations Density 0.094%

    No Known Activations