© 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. 19548
    Prev
    Next
    INDEX
    Explanations

    words ending in ig, rig, or lig

    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
    ract
    -0.10
    achment
    -0.10
    enment
    -0.10
    ozy
    -0.10
    rb
    -0.10
    ãĢĢ
    -0.10
    ráci
    -0.09
    éĢ¸
    -0.09
    κο
    -0.09
    æĮ¯
    -0.09
    POSITIVE LOGITS
    ging
    0.19
    keiten
    0.19
    idity
    0.16
    gle
    0.15
    orous
    0.15
    ged
    0.15
    gy
    0.15
    ths
    0.14
    ean
    0.13
    zag
    0.13
    Activations Density 0.054%

    No Known Activations