© 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. 24589
    Prev
    Next
    INDEX
    Explanations

    words ending in -lysis or -lyzed

    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
    ials
    -0.10
    nbsp
    -0.09
    uel
    -0.09
    íĹĮ
    -0.09
    wal
    -0.09
    ulk
    -0.09
    eller
    -0.09
    subst
    -0.09
    iken
    -0.09
    icip
    -0.09
    POSITIVE LOGITS
    sis
    0.21
    isis
    0.14
    ysis
    0.14
     sis
    0.12
    lation
    0.12
    zing
    0.12
    ester
    0.11
     cle
    0.11
    ested
    0.11
     est
    0.10
    Activations Density 0.006%

    No Known Activations