© 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. 27003
    Prev
    Next
    INDEX
    Explanations

    following dialogue or character names

    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
    ersh
    -0.10
     Tao
    -0.10
     reck
    -0.09
     shy
    -0.09
     legis
    -0.09
     Morg
    -0.09
     ÐļÑĢи
    -0.09
    annie
    -0.08
     mant
    -0.08
    ëĥ¥
    -0.08
    POSITIVE LOGITS
    legate
    0.10
     Advance
    0.10
     Ay
    0.10
     meth
    0.10
    Fetch
    0.09
    meth
    0.09
    oui
    0.09
     drum
    0.09
     Drum
    0.09
     Fetch
    0.09
    Activations Density 0.035%

    No Known Activations