© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 14547
    Prev
    Next
    INDEX
    Explanations

    largest and deepest freshwater lake

    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
     Euras
    -0.10
     Wolfgang
    -0.10
    arResult
    -0.09
     chol
    -0.08
    оÑĢÑĥ
    -0.08
     lith
    -0.08
     Boone
    -0.08
    çŃij
    -0.08
     Pick
    -0.08
     Lith
    -0.08
    POSITIVE LOGITS
    ë
    0.10
     settlement
    0.09
     Ner
    0.09
    è£ķ
    0.09
     militant
    0.09
     Lena
    0.09
    ä½³
    0.09
     Priest
    0.09
    ikit
    0.09
    Nov
    0.08
    Activations Density 0.022%

    No Known Activations