© 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. 8733
    Prev
    Next
    INDEX
    Explanations

    who has been eating

    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
     killing
    -0.11
     killings
    -0.10
    kill
    -0.10
    iddy
    -0.10
     kill
    -0.10
     kills
    -0.09
    漫
    -0.09
    ä¸īä¸īä¸īä¸ī
    -0.08
     lá»ĩ
    -0.08
     Killing
    -0.08
    POSITIVE LOGITS
     evil
    0.12
     chase
    0.11
     fo
    0.11
     mean
    0.11
     conn
    0.11
     foil
    0.11
     swipe
    0.11
     chased
    0.10
     Fo
    0.10
     nef
    0.10
    Activations Density 0.047%

    No Known Activations