© 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. 52417
    Prev
    Next
    INDEX
    Explanations

    checking if something is correct

    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
    idy
    -0.11
    ãĢĪ
    -0.10
    lick
    -0.10
    tos
    -0.10
    ilon
    -0.10
    stre
    -0.09
    å°±ä¼ļ
    -0.09
    ify
    -0.09
     guaranteed
    -0.09
     Slo
    -0.09
    POSITIVE LOGITS
     correctly
    0.28
     indeed
    0.27
     correct
    0.24
    æŃ£ç¡®
    0.23
     пÑĢавилÑĮно
    0.23
     correctamente
    0.20
     Äijúng
    0.20
     Correct
    0.19
    correct
    0.19
     successfully
    0.19
    Activations Density 0.045%

    No Known Activations