© 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. 32268
    Prev
    Next
    INDEX
    Explanations

    german dialectal phrases

    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
     Hoe
    -0.12
    hoe
    -0.12
     ​​
    -0.11
    irth
    -0.09
    arak
    -0.09
    ursor
    -0.09
    dT
    -0.08
    ights
    -0.08
    dıģında
    -0.08
    QUIRE
    -0.08
    POSITIVE LOGITS
    Ý
    0.12
    å¼Ĺ
    0.11
    ä»Ķ
    0.11
     da
    0.11
     fo
    0.11
     sku
    0.11
    enga
    0.11
    isch
    0.10
     dialect
    0.10
     dat
    0.10
    Activations Density 0.096%

    No Known Activations