© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35629
    Prev
    Next
    INDEX
    Explanations

    saying sorry

    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
     Uns
    -0.11
     SMA
    -0.09
    ount
    -0.09
     Sunny
    -0.09
    ...
    -0.09
    asure
    -0.08
    gon
    -0.08
     Abbey
    -0.08
     gam
    -0.08
     Flake
    -0.08
    POSITIVE LOGITS
     sorry
    0.34
     Sorry
    0.27
    sorry
    0.26
    Sorry
    0.26
    æĬ±
    0.21
     sor
    0.19
    SOR
    0.18
    orry
    0.17
     Sor
    0.14
    æŃ
    0.13
    Activations Density 0.080%

    No Known Activations