© 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. 55410
    Prev
    Next
    INDEX
    Explanations

    self affirmation

    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
    •LION

    No Comments

    Negative Logits
     guy
    -0.10
     heritage
    -0.09
     upright
    -0.09
     trav
    -0.09
     guys
    -0.09
    æ³
    -0.09
    737
    -0.09
     heartfelt
    -0.09
    evin
    -0.08
     ï¼¼:
    -0.08
    POSITIVE LOGITS
     receipts
    0.10
    stav
    0.10
    unicorn
    0.10
     unpopular
    0.10
     fucks
    0.10
     IG
    0.09
    linky
    0.09
    ocha
    0.09
     Bren
    0.09
    Pinterest
    0.09
    Activations Density 0.112%

    No Known Activations