© 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. 2404
    Prev
    Next
    INDEX
    Explanations

    months and dates

    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
     McKay
    -0.10
    -0.09
     Oct
    -0.09
    yth
    -0.09
    umas
    -0.08
    itech
    -0.08
    emy
    -0.08
    icks
    -0.08
    indle
    -0.08
    andler
    -0.08
    POSITIVE LOGITS
    份
    0.12
    202
    0.12
     isr
    0.10
    kiye
    0.09
    esa
    0.09
    âĶģ
    0.08
     cut
    0.08
    201
    0.08
    ade
    0.08
    ennen
    0.08
    Activations Density 0.001%

    No Known Activations