© 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. 44571
    Prev
    Next
    INDEX
    Explanations

    role play

    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
    -caret
    -0.10
     accompl
    -0.10
    ertools
    -0.09
    -metadata
    -0.09
    kes
    -0.09
     gal
    -0.09
     collabor
    -0.09
    rega
    -0.09
    ington
    -0.09
    -runtime
    -0.08
    POSITIVE LOGITS
    lessly
    0.17
    isify
    0.17
    inize
    0.15
    alyze
    0.14
    arily
    0.14
    etrize
    0.13
    itize
    0.13
    istically
    0.13
    aneously
    0.13
    entially
    0.13
    Activations Density 0.167%

    No Known Activations