© 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. 54920
    Prev
    Next
    INDEX
    Explanations

    rate, time, frequency, pace

    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
    utable
    -0.11
    sha
    -0.09
    624
    -0.09
    bern
    -0.09
    /about
    -0.08
    Æ°u
    -0.08
    |/
    -0.08
    (where
    -0.08
     Mah
    -0.08
    |array
    -0.08
    POSITIVE LOGITS
     manner
    0.13
     cui
    0.13
     mÃł
    0.12
     hvordan
    0.10
     коÑĤоÑĢÑĭм
    0.10
     VÅ¡ech
    0.09
     коÑĤоÑĢ
    0.09
     kter
    0.09
     kterým
    0.09
     Pik
    0.09
    Activations Density 0.114%

    No Known Activations