© 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. 18773
    Prev
    Next
    INDEX
    Explanations

    wenn/dass/während clause starter

    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
     Ihren
    -0.15
     aktuellen
    -0.12
     verschiedenen
    -0.12
     selber
    -0.11
     unseren
    -0.11
     Ekon
    -0.11
     meisten
    -0.11
     keinen
    -0.11
     Ihrem
    -0.11
     Woche
    -0.11
    POSITIVE LOGITS
     es
    0.16
     ich
    0.16
     sich
    0.16
     er
    0.15
     die
    0.14
     das
    0.13
     der
    0.13
     sie
    0.13
     alle
    0.12
     je
    0.12
    Activations Density 0.062%

    No Known Activations