© 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. 63226
    Prev
    Next
    INDEX
    Explanations

    feeling down, quite close, passionate

    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
    EMPLARY
    -0.12
    ¶Į
    -0.10
    .Formatter
    -0.10
    717
    -0.09
    ;:;:
    -0.09
    ©©
    -0.09
    ฺ
    -0.09
    íĸ
    -0.08
    TRGL
    -0.08
    ³Øª
    -0.08
    POSITIVE LOGITS
     gall
    0.10
     [âĢ¦
    0.08
    oga
    0.07
     reim
    0.07
     Neo
    0.07
    /owl
    0.07
    ertoire
    0.07
    lea
    0.07
     Sheldon
    0.07
    fore
    0.07
    Activations Density 0.003%

    No Known Activations