© 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. 36815
    Prev
    Next
    INDEX
    Explanations

    modal verb followed by action verb

    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
    kees
    -0.10
     Geh
    -0.10
     Again
    -0.10
     Confidential
    -0.09
     again
    -0.09
     Hun
    -0.09
     :|:
    -0.09
     spoon
    -0.09
    aina
    -0.09
    r
    -0.09
    POSITIVE LOGITS
    ï¼ģãĢį\n\n
    0.13
     totally
    0.11
    SURE
    0.11
     shall
    0.10
    ï¼ģ”;\n\n
    0.10
     guaranteed
    0.10
    ialias
    0.10
    ãģłãģ£ãģ¦
    0.09
    ä¸Ģå®ļ
    0.09
    ä¿Ŀè¯ģ
    0.09
    Activations Density 0.054%

    No Known Activations