© 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. 10778
    Prev
    Next
    INDEX
    Explanations

    bem como

    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
    hek
    -0.10
     Beard
    -0.09
    inge
    -0.09
    okrat
    -0.09
    =
    -0.08
    ategories
    -0.08
     Ved
    -0.08
    495
    -0.08
    CEL
    -0.08
     bzw
    -0.08
    POSITIVE LOGITS
    ãĤĪãģ³
    0.28
    以åıĬ
    0.27
     serta
    0.26
    ï¼Į以åıĬ
    0.22
     plus
    0.21
     sowie
    0.20
    è¿ĺæľī
    0.20
     oraz
    0.19
     samt
    0.17
     ainsi
    0.17
    Activations Density 0.022%

    No Known Activations