© 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. 43787
    Prev
    Next
    INDEX
    Explanations

    with respect and dignity

    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
     sincerity
    -0.10
     Ups
    -0.10
     hors
    -0.09
     Robertson
    -0.09
     Dy
    -0.09
     disbelief
    -0.09
    adem
    -0.09
     ÑģÑĤоÑĢон
    -0.08
     è³
    -0.08
    326
    -0.08
    POSITIVE LOGITS
     respect
    0.24
    respect
    0.17
     Ñĥв
    0.16
     Respect
    0.15
    outh
    0.15
    å°Ĭ
    0.14
     dignity
    0.14
     consideration
    0.13
    -res
    0.13
     civ
    0.13
    Activations Density 0.018%

    No Known Activations