© 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. 63185
    Prev
    Next
    INDEX
    Explanations

    one's, one another, one hand

    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
     one
    -0.19
    ä¹ĭä¸Ģ
    -0.14
     íķĺëĤĺ
    -0.13
     одной
    -0.12
     One
    -0.11
     ÛĮÚ©ÛĮ
    -0.11
     одна
    -0.10
     одне
    -0.10
     satu
    -0.10
    ä¸Ģ页
    -0.10
    POSITIVE LOGITS
    ida
    0.19
    onta
    0.17
    ir
    0.17
    -size
    0.16
    -offs
    0.16
    SELF
    0.16
     liners
    0.16
    -on
    0.15
    -off
    0.15
    -time
    0.15
    Activations Density 0.060%

    No Known Activations