© 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. 33475
    Prev
    Next
    INDEX
    Explanations

    understand after pronouns

    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
     compreh
    -0.11
     Guth
    -0.10
    umper
    -0.10
     Chore
    -0.09
    uan
    -0.09
    astes
    -0.09
    (withId
    -0.08
    regar
    -0.08
     Gut
    -0.08
     incons
    -0.08
    POSITIVE LOGITS
     know
    0.28
    çŁ¥éģĵ
    0.28
     knows
    0.28
     knew
    0.26
     biết
    0.23
     knowing
    0.22
     understand
    0.21
     зна
    0.21
     çŁ¥
    0.20
     wissen
    0.20
    Activations Density 0.071%

    No Known Activations