© 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. 60116
    Prev
    Next
    INDEX
    Explanations

    specific time durations

    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
    ged
    -0.10
     Aviv
    -0.10
    atr
    -0.09
    zin
    -0.09
    ness
    -0.09
    imar
    -0.09
    ond
    -0.09
    tright
    -0.09
     months
    -0.08
    ma
    -0.08
    POSITIVE LOGITS
    éIJĺ
    0.22
    uted
    0.18
    uet
    0.14
    glass
    0.13
    uten
    0.13
    éĴŁ
    0.13
    UTES
    0.13
    unte
    0.12
    ofday
    0.12
    -max
    0.12
    Activations Density 0.031%

    No Known Activations