© 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. 18246
    Prev
    Next
    INDEX
    Explanations

    new beginning, second chance

    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
     byt
    -0.10
    ologne
    -0.09
    lass
    -0.09
    èĬĻ
    -0.09
     nearest
    -0.09
    GINE
    -0.09
    ymm
    -0.08
    ãĤ
    -0.08
    GAN
    -0.08
     boredom
    -0.08
    POSITIVE LOGITS
     chance
    0.50
     second
    0.43
     Chance
    0.40
    Chance
    0.37
     opportunity
    0.36
     chances
    0.36
    second
    0.35
    Second
    0.31
     Second
    0.31
    _chance
    0.31
    Activations Density 0.059%

    No Known Activations