© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 19313
    Prev
    Next
    INDEX
    Explanations

    se cuenta de que

    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
    Negative Logits
     desar
    -0.15
     automáticamente
    -0.14
     pornô
    -0.14
     generado
    -0.14
     sigu
    -0.13
     acomp
    -0.13
     difÃŃc
    -0.12
    asse
    -0.12
     automát
    -0.11
     gross
    -0.11
    POSITIVE LOGITS
     se
    0.16
     y
    0.15
     nuest
    0.12
    ologÃŃa
    0.12
     lo
    0.12
     pract
    0.11
     si
    0.11
     ya
    0.10
     en
    0.10
    ayer
    0.10
    Activations Density 0.196%

    No Known Activations