© 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. 5702
    Prev
    Next
    INDEX
    Explanations

    designed to limit or specify

    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
     correctly
    -0.10
    надлеж
    -0.10
     usually
    -0.10
     Äijúng
    -0.10
     potentially
    -0.09
     almost
    -0.08
    ushi
    -0.08
     because
    -0.08
     Wallace
    -0.08
    ceae
    -0.08
    POSITIVE LOGITS
     say
    0.19
     perhaps
    0.17
    say
    0.17
     ÙħØ«ÙĦا
    0.16
    perhaps
    0.13
     instead
    0.13
     maybe
    0.12
     Perhaps
    0.12
     напÑĢимеÑĢ
    0.12
    haps
    0.12
    Activations Density 0.090%

    No Known Activations