© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 22218
    Prev
    Next
    INDEX
    Explanations

    respectful conversation or harmful content

    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
    &apos
    -0.09
    -0.07
    -\n
    -0.07
     [...
    -0.07
    à¹ĩว
    -0.07
     Uploaded
    -0.06
     zza
    -0.06
     guarante
    -0.06
    ...");č\n
    -0.06
    ?#
    -0.06
    POSITIVE LOGITS
    ¶Į
    0.11
    ÐIJÑĢÑħÑĸв
    0.09
     %[
    0.09
    ÂĢÂĢ
    0.09
     piger
    0.09
    -------------</
    0.09
    InSection
    0.09
    ----------</
    0.09
    Å¡ker
    0.09
     nalez
    0.09
    Activations Density 0.005%

    No Known Activations