© 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. 27814
    Prev
    Next
    INDEX
    Explanations

    friendly and ready descriptions

    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
    -powered
    -0.15
    -based
    -0.14
    -Based
    -0.14
    -led
    -0.13
    -dominated
    -0.13
    -generated
    -0.12
    -heavy
    -0.12
    -less
    -0.12
    -mediated
    -0.12
    -filled
    -0.12
    POSITIVE LOGITS
     friendly
    0.36
    friendly
    0.29
    -friendly
    0.28
     Friendly
    0.26
     ready
    0.23
     specific
    0.23
    riendly
    0.23
    Friendly
    0.22
     grade
    0.21
    ready
    0.21
    Activations Density 0.214%

    No Known Activations