© 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. 29753
    Prev
    Next
    INDEX
    Explanations

    significant portion or amount

    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
     dozen
    -0.09
     gấp
    -0.09
    InMillis
    -0.09
    eri
    -0.09
     yerleÅŁ
    -0.08
    []=$
    -0.08
     Verg
    -0.08
    spd
    -0.08
     orb
    -0.08
    roi
    -0.08
    POSITIVE LOGITS
     portion
    0.45
    portion
    0.32
     portions
    0.28
     fraction
    0.27
     proportion
    0.27
     percentage
    0.25
     majority
    0.25
     chunk
    0.24
     significant
    0.23
    éĥ¨åĪĨ
    0.21
    Activations Density 0.089%

    No Known Activations