© 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. 59708
    Prev
    Next
    INDEX
    Explanations

    German and Spanish connectors

    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
     herein
    -0.11
    kus
    -0.10
     Nah
    -0.09
    oÄŁ
    -0.09
     böylece
    -0.08
    575
    -0.08
    okie
    -0.08
    usty
    -0.08
    ãģĩ
    -0.08
    adian
    -0.08
    POSITIVE LOGITS
     thereof
    0.46
     ther
    0.40
    åħ¶ä¸Ń
    0.40
     davon
    0.31
     Ther
    0.26
     dess
    0.24
     ìĿ´ë¥¼
    0.21
    ãģĿãģĵ
    0.21
     بداÙĨ
    0.21
    ther
    0.21
    Activations Density 0.330%

    No Known Activations