© 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. 31192
    Prev
    Next
    INDEX
    Explanations

    quotation marks or similar punctuation

    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
    ’;T
    -0.11
    ’;\n\n
    -0.10
    ’;\n
    -0.10
    ;;\n
    -0.10
    ’;S
    -0.09
     
    -0.09
    ’;
    -0.09
     evet
    -0.09
    
    -0.09
     ['.
    -0.09
    POSITIVE LOGITS
     "
    0.43
     “;
    0.29
     «
    0.29
    ãĢĮ
    0.28
     ``
    0.22
     '
    0.22
     "$
    0.20
     ãĢĮ
    0.20
     âĢŀ
    0.19
     "_
    0.18
    Activations Density 0.425%

    No Known Activations