© 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. 39611
    Prev
    Next
    INDEX
    Explanations

    glad or sorry to hear that

    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
     proc
    -0.10
    æĢ§çļĦ
    -0.09
    olla
    -0.09
    inos
    -0.08
    داÙħ
    -0.08
    odon
    -0.08
    ij
    -0.08
    æł·çļĦ
    -0.08
    cene
    -0.08
    iple
    -0.08
    POSITIVE LOGITS
     bahwa
    0.14
     that
    0.12
     rằng
    0.11
     ÏĮÏĦι
    0.11
     eso
    0.10
     cela
    0.10
     Ø°ÙĦÙĥ
    0.10
     ça
    0.09
    that
    0.09
    꾸
    0.09
    Activations Density 0.012%

    No Known Activations