© 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. 39437
    Prev
    Next
    INDEX
    Explanations

    noun's noun

    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
    人类
    -0.12
    zelf
    -0.11
    å°ı说
    -0.11
    éĹ®é¢ĺ
    -0.10
    æĥħ
    -0.10
    人çļĦ
    -0.10
    ä¸Ģ覧
    -0.10
    人æīį
    -0.10
    大
    -0.10
    æĥħåĨµ
    -0.09
    POSITIVE LOGITS
    -eye
    0.18
     behalf
    0.13
     own
    0.13
     sake
    0.12
    ÂĢÂĻ
    0.12
    tring
    0.11
    ees
    0.11
    '
    0.11
     been
    0.11
    afe
    0.11
    Activations Density 0.053%

    No Known Activations