© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 27860
    Prev
    Next
    INDEX
    Explanations

    first AGI

    np_acts-logits-general · gemini-2.5-flash-lite

    references to AGI, especially phrasing about how the first AGI will be created or which model will become it.

    oai_token-act-pair · gpt-5
    Triggered by @vetterc0
    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
    Negative Logits
     robotic
    -0.10
     IDEA
    -0.10
    se
    -0.09
    jis
    -0.09
    VR
    -0.09
    ikel
    -0.09
    otto
    -0.09
    ाधन
    -0.08
    åIJī
    -0.08
     lev
    -0.08
    POSITIVE LOGITS
     AG
    0.21
     AI
    0.19
    AI
    0.16
    AG
    0.16
     consciousness
    0.15
     Artificial
    0.14
     artificial
    0.14
     intelligence
    0.13
     super
    0.12
     Kur
    0.12
    Activations Density 0.175%

    No Known Activations