© 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. 37264
    Prev
    Next
    INDEX
    Explanations

    inscription and writing

    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
     Coloring
    -0.14
     coloring
    -0.13
     numbered
    -0.11
     pronunciation
    -0.10
    sar
    -0.09
    _EDITOR
    -0.09
    PAD
    -0.08
    sik
    -0.08
    æ¡£
    -0.08
    .CustomButton
    -0.08
    POSITIVE LOGITS
     ins
    0.34
     inscription
    0.34
     writing
    0.32
     written
    0.31
     words
    0.29
     writings
    0.29
    inscription
    0.28
     напиÑģ
    0.26
    writing
    0.25
     wrote
    0.25
    Activations Density 0.176%

    No Known Activations