© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 12298
    Prev
    Next
    INDEX
    Explanations

    closing JSON structure

    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
     @[
    -0.10
    ,))\n
    -0.10
     Freeze
    -0.09
     />)\n
    -0.09
    ()))\n\n
    -0.09
    ippy
    -0.09
    '))\n
    -0.09
     ""))\n
    -0.09
    itos
    -0.08
    >())\n
    -0.08
    POSITIVE LOGITS
    },\n
    0.27
     },\n
    0.27
    ),\n
    0.26
    "},\n
    0.25
    "],\n
    0.25
    ],\n
    0.24
    "),\n
    0.24
    '],\n
    0.23
    '),\n
    0.23
     ),\n
    0.22
    Activations Density 0.075%

    No Known Activations