© 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. 13092
    Prev
    Next
    INDEX
    Explanations

    assistant refusals

    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
     Laud
    -0.10
    ©
    -0.10
     CO
    -0.09
    ystal
    -0.09
    icer
    -0.09
     Laur
    -0.09
     heels
    -0.09
    -
    -0.09
    lee
    -0.09
    \n
    -0.08
    POSITIVE LOGITS
    ä¸įèĥ½
    0.11
    _exempt
    0.10
     cannot
    0.10
    annot
    0.10
     putt
    0.09
    ampp
    0.09
     unb
    0.09
    ÑĢеменно
    0.09
    å¾ĭ
    0.09
    ensburg
    0.08
    Activations Density 0.098%

    No Known Activations