© 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. 32375
    Prev
    Next
    INDEX
    Explanations

    respectful professional tone

    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
     Kre
    -0.09
    itto
    -0.09
     Î
    -0.09
    /current
    -0.09
    ÑĥÑĢÑģ
    -0.08
    audi
    -0.08
     and
    -0.08
    ë¥´ê³ł
    -0.08
    ebra
    -0.08
     Moody
    -0.08
    POSITIVE LOGITS
     manner
    0.19
     tone
    0.14
     environment
    0.13
     atmosphere
    0.12
     approach
    0.12
     space
    0.11
    æ°
    0.11
     atmos
    0.10
     convers
    0.10
     tones
    0.10
    Activations Density 0.047%

    No Known Activations