© 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. 46014
    Prev
    Next
    INDEX
    Explanations

    allows or supports functionality

    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
    anteed
    -0.11
    oker
    -0.10
    _DISABLED
    -0.10
     Assistance
    -0.09
     ÑĥÑħ
    -0.09
     exhausting
    -0.08
    akit
    -0.08
    .osgi
    -0.08
    ноÑİ
    -0.08
     serg
    -0.08
    POSITIVE LOGITS
     allow
    0.41
     allows
    0.39
     supports
    0.38
    åħģ
    0.34
    allow
    0.33
    æĶ¯æĮģ
    0.33
     allowing
    0.32
     support
    0.32
     Allows
    0.30
    supports
    0.30
    Activations Density 0.192%

    No Known Activations