© 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. 2944
    Prev
    Next
    INDEX
    Explanations

    Moroccan darija greetings

    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
     Armenian
    -0.11
     Osman
    -0.11
    lesi
    -0.10
     Armenia
    -0.10
     Persian
    -0.10
    .lo
    -0.09
     Albania
    -0.09
     Mahm
    -0.09
     Alabama
    -0.09
     Tor
    -0.09
    POSITIVE LOGITS
     Morocco
    0.25
     Marr
    0.24
     Moroccan
    0.23
     Atlas
    0.23
    Mor
    0.22
     اÙĦÙħغرب
    0.20
    Atlas
    0.20
     Ber
    0.16
     Cas
    0.16
     Rif
    0.15
    Activations Density 0.041%

    No Known Activations