© 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. 27705
    Prev
    Next
    INDEX
    Explanations

    ups and downs

    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
     hardships
    -0.12
     anomaly
    -0.11
     hardship
    -0.10
    SEN
    -0.09
     caval
    -0.09
     nightmares
    -0.08
     Crossing
    -0.08
    zn
    -0.08
     stif
    -0.08
    enda
    -0.08
    POSITIVE LOGITS
     ups
    0.48
    ups
    0.38
     Ups
    0.37
    Ups
    0.36
     highs
    0.36
    UPS
    0.28
     UPS
    0.25
     roller
    0.25
    -ups
    0.24
     Roller
    0.23
    Activations Density 0.126%

    No Known Activations