© 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. 34406
    Prev
    Next
    INDEX
    Explanations

    pride, ambition, ego

    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
     irresponsible
    -0.11
    Mismatch
    -0.10
    394
    -0.09
     Inspiration
    -0.09
     depreci
    -0.09
    ines
    -0.09
    _tid
    -0.09
     gent
    -0.09
    åħ´
    -0.09
     instinct
    -0.08
    POSITIVE LOGITS
     hub
    0.30
     Pride
    0.26
     pride
    0.26
    hub
    0.23
     Hub
    0.22
     ambition
    0.21
    Hub
    0.20
     eg
    0.19
     ego
    0.19
     cov
    0.19
    Activations Density 0.103%

    No Known Activations