© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 17270
    Prev
    Next
    INDEX
    Explanations

    defining nouns after determiners

    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
    baugh
    -0.09
    achable
    -0.09
     Sap
    -0.08
    ãĤĥ
    -0.08
     profess
    -0.07
    852
    -0.07
     Leak
    -0.07
    634
    -0.07
    borne
    -0.07
    ledge
    -0.07
    POSITIVE LOGITS
    âĨĵ
    0.09
     McInt
    0.09
    (compact
    0.09
    roupon
    0.08
    олог
    0.08
     Tanner
    0.08
    onet
    0.08
    (us
    0.08
    enko
    0.08
    ldre
    0.08
    Activations Density 0.093%

    No Known Activations