© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 34828
    Prev
    Next
    INDEX
    Explanations

    refusal or not wanting something

    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
    .isTrue
    -0.10
     ware
    -0.09
    Streamer
    -0.09
    ocz
    -0.08
     lateral
    -0.08
    ÙĪØ·
    -0.08
    ète
    -0.08
    ï½Į
    -0.08
     unsett
    -0.08
    >NN
    -0.08
    POSITIVE LOGITS
     anymore
    0.22
     participation
    0.13
     further
    0.13
     nữa
    0.12
    æŁIJ
    0.12
     particular
    0.11
     obligation
    0.11
     participate
    0.11
     continuation
    0.10
     Participation
    0.10
    Activations Density 0.092%

    No Known Activations