© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 5718
    Prev
    Next
    INDEX
    Explanations

    confidence in my ability

    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
    Negative Logits
    wcs
    -0.11
    utin
    -0.09
    agy
    -0.09
     Accountability
    -0.09
    314
    -0.09
    ended
    -0.08
    coder
    -0.08
     grace
    -0.08
     heaven
    -0.08
    ãģ«ãģ¨
    -0.08
    POSITIVE LOGITS
     abilities
    0.32
     ability
    0.30
     Abilities
    0.23
     Ability
    0.22
    Ability
    0.20
    èĥ½åĬĽ
    0.19
    abilities
    0.18
    _ability
    0.18
     capabilities
    0.16
     khả
    0.15
    Activations Density 0.039%

    No Known Activations