© 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. 26145
    Prev
    Next
    INDEX
    Explanations

    `une` or `una` before a noun

    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
     aspect
    -0.10
     one
    -0.10
     gente
    -0.10
    avier
    -0.10
    ä¸Ģ个
    -0.09
     confl
    -0.09
    toy
    -0.09
     talent
    -0.09
    crement
    -0.09
     culo
    -0.09
    POSITIVE LOGITS
     autre
    0.12
     altro
    0.11
     delle
    0.11
     Certain
    0.11
    /all
    0.11
    maal
    0.11
     certain
    0.11
    ike
    0.10
     Saga
    0.10
    ाध
    0.10
    Activations Density 0.110%

    No Known Activations