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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 33750
    Prev
    Next
    INDEX
    Explanations

    serious or "che non"

    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
     Extremely
    -0.09
    oku
    -0.09
     frankly
    -0.09
    _WP
    -0.09
    lx
    -0.09
    okies
    -0.09
    edo
    -0.09
    asy
    -0.08
    éĿ
    -0.08
     recru
    -0.08
    POSITIVE LOGITS
     serious
    0.82
     seriousness
    0.71
     Serious
    0.67
    serious
    0.65
     seriously
    0.51
     ÑģеÑĢÑĮез
    0.49
     ÑģеÑĢÑĮ
    0.44
     ciddi
    0.43
     Seriously
    0.42
     ern
    0.41
    Activations Density 0.143%

    No Known Activations