© 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. 3227
    Prev
    Next
    INDEX
    Explanations

    negation

    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
     necessarily
    -0.12
    zin
    -0.11
     Fam
    -0.11
     fung
    -0.09
    ocker
    -0.09
     concrete
    -0.09
     precious
    -0.09
    ecessarily
    -0.09
    usan
    -0.09
    405
    -0.09
    POSITIVE LOGITS
    ught
    0.11
    rary
    0.11
    BYTES
    0.09
    withstanding
    0.09
    ueva
    0.09
    ãģ£ãģı
    0.09
    ä¸Ŀ
    0.09
     nor
    0.09
    alg
    0.09
     Perc
    0.09
    Activations Density 0.074%

    No Known Activations