© 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. 15232
    Prev
    Next
    INDEX
    Explanations

    that is | Es decir | ou seja | das heiÃŁt | c'est-Ãł-dire

    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
    ees
    -0.10
    ̣
    -0.10
    apat
    -0.09
    idge
    -0.09
     nay
    -0.09
    asse
    -0.08
    583
    -0.08
    важ
    -0.08
     Swarm
    -0.08
    oden
    -0.08
    POSITIVE LOGITS
    ì¦
    0.21
    å°±æĺ¯
    0.20
     ì¦ī
    0.19
     tức
    0.19
    عÙĨÛĮ
    0.19
     yani
    0.19
     decir
    0.19
    .e
    0.19
     Yani
    0.18
     δη
    0.18
    Activations Density 0.068%

    No Known Activations