© 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. 60106
    Prev
    Next
    INDEX
    Explanations

    consistency is key

    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
     daytime
    -0.09
     discord
    -0.09
     diam
    -0.09
     Griff
    -0.09
    imd
    -0.09
     Fet
    -0.09
    ï¾Į
    -0.09
    оки
    -0.08
     ngh
    -0.08
    istrovstvÃŃ
    -0.08
    POSITIVE LOGITS
     consistency
    0.34
     consistent
    0.28
    consistent
    0.25
     regular
    0.24
    istency
    0.23
     frequency
    0.23
     Cons
    0.22
     Regular
    0.22
     commitment
    0.20
     Frequency
    0.20
    Activations Density 0.068%

    No Known Activations