© 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. 28637
    Prev
    Next
    INDEX
    Explanations

    begging, pleading, urging

    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
    ABLE
    -0.12
    quil
    -0.10
     Fuller
    -0.09
    apes
    -0.09
    Bezier
    -0.09
    _PF
    -0.09
    ered
    -0.09
     Pill
    -0.08
    ABEL
    -0.08
    paque
    -0.08
    POSITIVE LOGITS
     mercy
    0.17
     Mercy
    0.14
    Merc
    0.14
    ging
    0.13
     Beg
    0.12
    gar
    0.12
     merc
    0.12
     beg
    0.11
     Merc
    0.10
    Bitte
    0.10
    Activations Density 0.023%

    No Known Activations