© 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. 18792
    Prev
    Next
    INDEX
    Explanations

    effect, efficiency, effable

    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
    ade
    -0.11
    erer
    -0.11
    ATIONAL
    -0.11
    acades
    -0.10
    otes
    -0.10
    ICATION
    -0.09
    ous
    -0.09
    erot
    -0.09
    rer
    -0.09
    ocommerce
    -0.09
    POSITIVE LOGITS
     eff
    0.21
     Eff
    0.19
    erves
    0.17
    à¸´à¸łà¸²à¸ŀ
    0.17
    eff
    0.17
    ector
    0.16
    orts
    0.15
    iciency
    0.15
    -eff
    0.15
    fect
    0.15
    Activations Density 0.020%

    No Known Activations