© 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. 41083
    Prev
    Next
    INDEX
    Explanations

    regret/decision to resign

    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
    æĹ¢
    -0.10
     stub
    -0.09
    obe
    -0.09
    weis
    -0.09
     compromise
    -0.09
    ãĤĮãģ°
    -0.09
     refused
    -0.08
    ide
    -0.08
     refuses
    -0.08
    /Graphics
    -0.08
    POSITIVE LOGITS
     reg
    0.21
     regret
    0.17
    Unfortunately
    0.13
     leider
    0.13
    éģĹ
    0.12
     Reg
    0.11
     hereby
    0.11
     Unfortunately
    0.11
     necessity
    0.10
    rego
    0.10
    Activations Density 0.095%

    No Known Activations