© 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. 50602
    Prev
    Next
    INDEX
    Explanations

    vs. versus comparisons

    np_acts-logits-general · gemini-2.5-flash-lite

    structures that mark comparisons or enumerations, like parenthetical matchups, numbered/bulleted items, and coordinated lists.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     ragaz
    -0.09
    }elseif
    -0.09
    styleType
    -0.09
    actionDate
    -0.08
    .scalablytyped
    -0.08
    ceptar
    -0.08
     )\n\n\n\n\n\n\n\n
    -0.08
    printStats
    -0.08
     salopes
    -0.07
     olup
    -0.07
    POSITIVE LOGITS
     tieten
    0.07
    jÃŃm
    0.07
    [âĢ¦
    0.07
    [source
    0.06
     iff
    0.06
    à¸ĸม
    0.06
     ?>\n\n\n
    0.06
    âķĹ
    0.06
    в
    0.06
    .htm
    0.06
    Activations Density 5.832%

    No Known Activations