© 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. 16415
    Prev
    Next
    INDEX
    Explanations

    she to take action

    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
    ÑĮ
    -0.09
     pic
    -0.09
    507
    -0.09
    amic
    -0.08
     rud
    -0.08
     Tang
    -0.08
     abandonment
    -0.08
    lassen
    -0.08
     pro
    -0.08
    enta
    -0.08
    POSITIVE LOGITS
     doing
    0.24
     Doing
    0.18
    åģļ
    0.17
     done
    0.16
    doing
    0.16
     اÙĨجاÙħ
    0.16
    Doing
    0.15
     melakukan
    0.14
     implementation
    0.13
    å®ŀæĸ½
    0.13
    Activations Density 0.138%

    No Known Activations