© 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. 36677
    Prev
    Next
    INDEX
    Explanations

    software and programming languages

    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
    Ùĭ
    -0.09
    _Tis
    -0.09
    аÑĤом
    -0.09
    опаÑģ
    -0.09
     nhau
    -0.08
    .XR
    -0.08
    ighbor
    -0.08
    Printf
    -0.08
    ĵ¨
    -0.08
    InParameter
    -0.08
    POSITIVE LOGITS
    s
    0.11
    -Benz
    0.11
    ®
    0.10
    ista
    0.10
    verse
    0.10
    /MPL
    0.09
    ®,
    0.09
    ï¸ı
    0.09
    /Linux
    0.09
     ther
    0.09
    Activations Density 0.148%

    No Known Activations