© 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. 51575
    Prev
    Next
    INDEX
    Explanations

    one or two

    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
    -three
    -0.12
    oren
    -0.11
    lla
    -0.10
    ä¸īä¸ī
    -0.09
    è¿ĻäºĽ
    -0.09
     trio
    -0.09
     THREE
    -0.09
    ä¸ī
    -0.08
    three
    -0.08
     ALL
    -0.08
    POSITIVE LOGITS
     one
    0.46
    ä¹ĭä¸Ģ
    0.33
     ÛĮÚ©ÛĮ
    0.33
     Both
    0.27
     both
    0.27
     beide
    0.26
    åħ¶ä¸Ń
    0.26
     neither
    0.25
     одного
    0.25
     salah
    0.25
    Activations Density 0.245%

    No Known Activations