© 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. 19432
    Prev
    Next
    INDEX
    Explanations

    response times and rates

    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
     timed
    -0.10
    íķŃ
    -0.10
     Timing
    -0.10
    é¼
    -0.10
     Wagner
    -0.10
    -era
    -0.10
     temporal
    -0.09
    Temporal
    -0.09
    ãĤ
    -0.09
     chronological
    -0.09
    POSITIVE LOGITS
     times
    0.40
    times
    0.25
     time
    0.25
     Times
    0.24
     rate
    0.23
     speed
    0.23
    Times
    0.21
    -times
    0.21
     rates
    0.20
    次æķ°
    0.19
    Activations Density 0.082%

    No Known Activations