© 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. 39581
    Prev
    Next
    INDEX
    Explanations

    uniformity and consistency

    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
     condensed
    -0.08
     punctuation
    -0.08
     bib
    -0.08
     ro
    -0.08
     Bug
    -0.08
     Bib
    -0.08
     redistrib
    -0.08
     stabbing
    -0.08
    .BackgroundImageLayout
    -0.08
     redistributed
    -0.08
    POSITIVE LOGITS
     uniform
    0.56
     standard
    0.41
    uniform
    0.40
     Uniform
    0.40
    Uniform
    0.38
    绣
    0.37
    standard
    0.33
    .uniform
    0.33
     Standard
    0.31
     ÑģÑĤанд
    0.30
    Activations Density 0.181%

    No Known Activations