© 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. 60397
    Prev
    Next
    INDEX
    Explanations

    Dutch articles followed by nouns

    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
     meisje
    -0.20
     dikke
    -0.19
     tiener
    -0.15
     vrou
    -0.14
     gezocht
    -0.13
     ontvangst
    -0.12
     mooie
    -0.12
     meisjes
    -0.12
     zwarte
    -0.11
    ̣
    -0.11
    POSITIVE LOGITS
     knull
    0.14
     door
    0.13
    ontvangst
    0.12
    uren
    0.11
    mpjes
    0.11
     ste
    0.11
     breed
    0.10
     pornofilm
    0.10
    oor
    0.10
     cq
    0.10
    Activations Density 0.022%

    No Known Activations