© 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. 62844
    Prev
    Next
    INDEX
    Explanations

    van de en het

    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
     dikke
    -0.21
     gezocht
    -0.18
     mooie
    -0.16
     meisjes
    -0.16
     tiener
    -0.16
     ontvangst
    -0.16
     vlak
    -0.15
     vrou
    -0.15
     meisje
    -0.14
     zwarte
    -0.14
    POSITIVE LOGITS
    ontvangst
    0.20
     knull
    0.18
     door
    0.16
     neuken
    0.16
     kutje
    0.15
     van
    0.15
    uit
    0.15
     é
    0.14
     en
    0.14
     het
    0.14
    Activations Density 0.072%

    No Known Activations