© 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. 971
    Prev
    Next
    INDEX
    Explanations

    noun followed by "that"

    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
    inct
    -0.10
     Wir
    -0.10
     having
    -0.09
     Mant
    -0.09
     mant
    -0.08
    aData
    -0.08
    .
    -0.08
     pan
    -0.08
    ampions
    -0.08
    OLER
    -0.08
    POSITIVE LOGITS
     that
    0.13
     ÏĢοÏħ
    0.12
    that
    0.11
     whose
    0.11
     Contents
    0.09
    <quote
    0.09
     Ú©Ùĩ
    0.09
    rale
    0.09
     intended
    0.09
     Buchanan
    0.09
    Activations Density 0.102%

    No Known Activations