© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 5730
    Prev
    Next
    INDEX
    Explanations

    politely ask for things

    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
    Negative Logits
    olle
    -0.10
    Absent
    -0.09
    ktop
    -0.09
     inv
    -0.09
    isco
    -0.08
    mutable
    -0.08
    anja
    -0.08
     Äijôi
    -0.08
     UNS
    -0.08
    à¤Ĺर
    -0.08
    POSITIVE LOGITS
     feel
    0.32
     Feel
    0.30
    Feel
    0.29
    feel
    0.27
     don
    0.21
     feels
    0.19
     Äijá»
    0.16
     please
    0.16
    ä¸įè¦ģ
    0.15
     felt
    0.15
    Activations Density 0.015%

    No Known Activations