© 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. 46183
    Prev
    Next
    INDEX
    Explanations

    first, let's discuss

    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
     ALSO
    -0.11
    inue
    -0.10
    iga
    -0.09
     finally
    -0.09
     dále
    -0.09
     ultimately
    -0.09
     ì²ĺìĿĮ
    -0.09
    _Ptr
    -0.09
     εÏĢίÏĥηÏĤ
    -0.09
    enga
    -0.08
    POSITIVE LOGITS
     lets
    0.11
     foremost
    0.10
     define
    0.10
     definitions
    0.10
     understand
    0.10
     tiên
    0.10
     establish
    0.10
    æĥ³åĪ°
    0.09
    note
    0.09
     Last
    0.09
    Activations Density 0.100%

    No Known Activations