© 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. 34291
    Prev
    Next
    INDEX
    Explanations

    the improvement of quality

    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
     responsiveness
    -0.12
     suitability
    -0.12
    keh
    -0.11
     attractiveness
    -0.11
    sembled
    -0.09
     fug
    -0.09
    лади
    -0.09
     viability
    -0.09
    /dashboard
    -0.08
    acles
    -0.08
    POSITIVE LOGITS
     overall
    0.23
     quality
    0.19
    overall
    0.19
     chances
    0.19
     speed
    0.19
     efficiency
    0.17
     odds
    0.16
     Overall
    0.15
    quality
    0.15
     accuracy
    0.14
    Activations Density 0.050%

    No Known Activations