© 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. 54830
    Prev
    Next
    INDEX
    Explanations

    asking someone to do something

    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
     Own
    -0.10
    _exempt
    -0.09
    prak
    -0.08
    มà¸ķ
    -0.08
    utin
    -0.08
    egan
    -0.08
     oneself
    -0.08
    outh
    -0.08
     cleaner
    -0.08
    еÑı
    -0.08
    POSITIVE LOGITS
     properly
    0.12
    ä¸Ģä¸ĭ
    0.12
    promise
    0.11
     promise
    0.11
    onces
    0.10
    -нибÑĥдÑĮ
    0.10
     something
    0.10
    çľĭçľĭ
    0.09
    strand
    0.09
    something
    0.09
    Activations Density 0.071%

    No Known Activations