© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33456
    Prev
    Next
    INDEX
    Explanations

    diff between

    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
     sight
    -0.10
     Tham
    -0.10
    amar
    -0.09
    udo
    -0.09
     Lamar
    -0.09
     Gamer
    -0.09
    dec
    -0.09
    ÃŃn
    -0.09
     Weiss
    -0.09
     hidden
    -0.09
    POSITIVE LOGITS
     diff
    0.29
    å·®
    0.24
    diff
    0.23
     Diff
    0.23
     differences
    0.22
    (diff
    0.22
     dif
    0.21
    Diff
    0.20
    .diff
    0.20
     difference
    0.19
    Activations Density 0.101%

    No Known Activations