© 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. 54540
    Prev
    Next
    INDEX
    Explanations

    multi-language words and their common follow-ups

    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
     aforementioned
    -0.09
     ÑĤабли
    -0.08
    оÑĢаÑı
    -0.07
    .moveToNext
    -0.07
    utut
    -0.07
    ModelProperty
    -0.07
    емаÑĤи
    -0.07
    âĶ¬
    -0.07
    ongan
    -0.06
     ìĹ°ëĿ½
    -0.06
    POSITIVE LOGITS
    ÐIJÑĢÑħÑĸв
    0.10
    ALAR
    0.08
     ìĪĺê°Ģ
    0.08
    ,\n\n\n\n
    0.07
     (!((
    0.07
    isContained
    0.07
     ð
    0.07
    aset
    0.07
    anager
    0.07
    589
    0.07
    Activations Density 0.297%

    No Known Activations