© 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. 23373
    Prev
    Next
    INDEX
    Explanations

    word origins from ancient languages

    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
    717
    -0.10
    235
    -0.09
     Hiro
    -0.08
     знаком
    -0.08
    çīĪ
    -0.08
    inx
    -0.08
     Crest
    -0.08
    ewood
    -0.08
    ripp
    -0.08
     Stard
    -0.08
    POSITIVE LOGITS
     Greek
    0.15
     Old
    0.14
     earlier
    0.14
     Latin
    0.13
     French
    0.13
     ancient
    0.12
     Middle
    0.11
     older
    0.11
     Sans
    0.11
     Äijâu
    0.11
    Activations Density 0.136%

    No Known Activations