© 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. 16448
    Prev
    Next
    INDEX
    Explanations

    sequence of words after newlines

    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
    opa
    -0.11
    \n\n
    -0.09
     unb
    -0.09
     vil
    -0.08
    961
    -0.08
    iman
    -0.08
    $I
    -0.08
     mysterious
    -0.08
     EM
    -0.08
    GenerationStrategy
    -0.08
    POSITIVE LOGITS
     cog
    0.10
    jet
    0.09
    iliz
    0.09
    611
    0.08
    \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
    0.08
    oned
    0.08
    yor
    0.08
    ussy
    0.08
    ubar
    0.08
    uddy
    0.08
    Activations Density 0.153%

    No Known Activations