© 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. 20502
    Prev
    Next
    INDEX
    Explanations

    attracting or conquering someone

    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
     delight
    -0.11
     Rocks
    -0.09
     Mock
    -0.09
     Searches
    -0.09
     oblig
    -0.09
     author
    -0.09
     delights
    -0.08
    ÙħÙĪÙĦ
    -0.08
     disappoint
    -0.08
    infeld
    -0.08
    POSITIVE LOGITS
     sed
    0.38
     Sed
    0.31
    sed
    0.27
     sediment
    0.19
    SED
    0.19
     conquest
    0.17
     charm
    0.16
     sedan
    0.15
    charm
    0.15
     Charm
    0.14
    Activations Density 0.158%

    No Known Activations