© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 61366
    Prev
    Next
    INDEX
    Explanations

    contribution to success

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Guerr
    -0.10
    812
    -0.09
     Companion
    -0.09
     ÏĩÏģη
    -0.09
    033
    -0.08
    -inst
    -0.08
     èģĶ
    -0.08
    760
    -0.08
    igs
    -0.08
    iele
    -0.08
    POSITIVE LOGITS
     contribution
    0.70
     contributions
    0.68
     Contribution
    0.54
     Contributions
    0.50
    contrib
    0.47
     contributed
    0.47
     contrib
    0.46
    Contrib
    0.46
     contribute
    0.45
     CONTRIBUT
    0.42
    Activations Density 0.130%

    No Known Activations