© 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. 38492
    Prev
    Next
    INDEX
    Explanations

    nothing, Not, nowhere, nada, rien

    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
    aro
    -0.10
    abol
    -0.09
    okers
    -0.08
    inker
    -0.08
     wsz
    -0.08
    isha
    -0.08
    ousse
    -0.08
    uti
    -0.08
    nage
    -0.08
    oker
    -0.08
    POSITIVE LOGITS
     nothing
    0.94
     Nothing
    0.77
    nothing
    0.76
     NOTHING
    0.72
    Nothing
    0.70
     nichts
    0.64
     nada
    0.62
     rien
    0.56
     ниÑĩего
    0.54
     nulla
    0.39
    Activations Density 0.211%

    No Known Activations