© 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. 36374
    Prev
    Next
    INDEX
    Explanations

    to make amends

    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
     sympathy
    -0.11
    è¤
    -0.09
     sympath
    -0.09
     lia
    -0.09
    avad
    -0.09
     politely
    -0.09
     groom
    -0.08
    anna
    -0.08
     rude
    -0.08
     Bauer
    -0.08
    POSITIVE LOGITS
     patch
    0.23
     reconciliation
    0.21
     mend
    0.21
     Patch
    0.20
    conciliation
    0.19
    patch
    0.19
     patched
    0.18
     Mend
    0.18
     olive
    0.18
     repair
    0.17
    Activations Density 0.060%

    No Known Activations