© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 1750
    Prev
    Next
    INDEX
    Explanations

    to the detrimentto the bestto your satisfactionto that end

    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
    Uvs
    -0.11
    kud
    -0.11
    463
    -0.11
    emain
    -0.09
    ulin
    -0.09
    -lang
    -0.09
    ë¶ĢíĦ°
    -0.09
     outset
    -0.09
     reins
    -0.09
     Chow
    -0.08
    POSITIVE LOGITS
     extent
    0.38
     tune
    0.37
     detriment
    0.32
    extent
    0.27
     Tune
    0.25
     liking
    0.21
    Extent
    0.21
     extents
    0.21
     tunes
    0.20
     satisfaction
    0.19
    Activations Density 0.128%

    No Known Activations