© 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. 19178
    Prev
    Next
    INDEX
    Explanations

    two independent samples

    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
     tri
    -0.10
     reserve
    -0.09
    ignet
    -0.09
     Claude
    -0.09
     :/:
    -0.09
    ingular
    -0.09
     fatal
    -0.09
     ranged
    -0.09
     appar
    -0.08
     âĮĴ
    -0.08
    POSITIVE LOGITS
     mean
    0.18
     Means
    0.18
     means
    0.15
    mean
    0.15
    Means
    0.14
     population
    0.13
     Mean
    0.13
     treatments
    0.13
     samples
    0.13
     groups
    0.13
    Activations Density 0.043%

    No Known Activations