© 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. 30878
    Prev
    Next
    INDEX
    Explanations

    beliefs of superiority and entitlement

    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
     Beaut
    -0.09
    åħĭæĸ¯
    -0.09
    ongyang
    -0.09
    445
    -0.09
     dubbed
    -0.09
     dign
    -0.08
     Boyle
    -0.08
    illard
    -0.08
    éŃĤ
    -0.08
    raith
    -0.08
    POSITIVE LOGITS
     superior
    0.25
     superiority
    0.19
     Superior
    0.18
     inv
    0.16
     entitled
    0.16
     above
    0.16
     ABOVE
    0.14
    above
    0.13
     clever
    0.13
     Above
    0.13
    Activations Density 0.069%

    No Known Activations