© 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. 42469
    Prev
    Next
    INDEX
    Explanations

    giving compliments or kind words

    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
     Impress
    -0.12
     greetings
    -0.10
    æģ¨
    -0.09
     applauded
    -0.09
    _Syntax
    -0.09
    .Hex
    -0.09
     è»
    -0.09
    phinx
    -0.08
    622
    -0.08
    exas
    -0.08
    POSITIVE LOGITS
     compliment
    0.38
     complement
    0.38
     compliments
    0.27
     fl
    0.26
     comple
    0.26
     complimentary
    0.25
     comments
    0.21
     Com
    0.19
    Com
    0.18
     comment
    0.18
    Activations Density 0.122%

    No Known Activations