© 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. 15791
    Prev
    Next
    INDEX
    Explanations

    language, languages, dialect

    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
     Lookup
    -0.10
     semantic
    -0.09
     Unicode
    -0.09
    Unicode
    -0.09
     lcm
    -0.09
    semantic
    -0.09
     wording
    -0.09
     pumps
    -0.09
    åĨĨ
    -0.09
    unicode
    -0.09
    POSITIVE LOGITS
     language
    0.34
     languages
    0.29
    è¯Ńè¨Ģ
    0.26
     ÑıзÑĭ
    0.23
     dialect
    0.23
     Language
    0.23
    language
    0.23
     γλÏİ
    0.21
    languages
    0.20
    Language
    0.20
    Activations Density 0.253%

    No Known Activations