© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 30823
    Prev
    Next
    INDEX
    Explanations

    paired items or concepts

    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
    uger
    -0.10
    uce
    -0.10
    ê³µì§Ģ
    -0.09
    rosse
    -0.09
     either
    -0.09
    /release
    -0.08
     khác
    -0.08
    zo
    -0.08
     Alleg
    -0.08
    on
    -0.08
    POSITIVE LOGITS
     sides
    0.25
    /all
    0.23
     ends
    0.23
     sexes
    0.19
    /e
    0.17
    /ne
    0.16
     Ends
    0.16
     directions
    0.15
    eted
    0.15
    rops
    0.13
    Activations Density 0.024%

    No Known Activations