© 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. 17497
    Prev
    Next
    INDEX
    Explanations

    excess or disproportionate amounts

    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
     sufficiently
    -0.10
    zem
    -0.09
     bastante
    -0.09
    '´
    -0.09
     worse
    -0.09
    usta
    -0.09
     imperson
    -0.09
    resh
    -0.09
     reasonably
    -0.09
     assez
    -0.09
    POSITIVE LOGITS
     excess
    0.25
     dispro
    0.19
     excessive
    0.19
     too
    0.19
    ãģĻãģİ
    0.17
     ì§ĢëĤĺ
    0.17
     ÑģлиÑĪком
    0.17
     demasi
    0.17
    cessive
    0.16
     quá
    0.16
    Activations Density 0.132%

    No Known Activations