© 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. 35492
    Prev
    Next
    INDEX
    Explanations

    probability and percentages

    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
    YPE
    -0.10
     Dodd
    -0.09
     Wein
    -0.09
    ouch
    -0.09
    kins
    -0.09
    \n
    -0.09
    etail
    -0.09
     tane
    -0.08
     Tale
    -0.08
    inx
    -0.08
    POSITIVE LOGITS
    iles
    0.18
    ages
    0.15
     chance
    0.14
    ile
    0.14
     νεÏĨοκάλÏħÏĪηÏĤ
    0.13
     percent
    0.12
    ual
    0.11
    uali
    0.11
    imeter
    0.11
     discount
    0.11
    Activations Density 0.044%

    No Known Activations