© 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. 11853
    Prev
    Next
    INDEX
    Explanations

    writing styles and syntax

    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
     gramm
    -0.09
     Topic
    -0.08
     Phonetic
    -0.08
    arsi
    -0.08
    itlement
    -0.08
    946
    -0.08
    oder
    -0.08
    aktion
    -0.08
     Span
    -0.08
     Props
    -0.08
    POSITIVE LOGITS
     writing
    0.42
    writing
    0.29
     Writing
    0.29
    Writing
    0.26
     writings
    0.25
    åĨĻ
    0.24
     communication
    0.23
     writ
    0.23
    -writing
    0.22
     written
    0.21
    Activations Density 0.229%

    No Known Activations