© 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. 35754
    Prev
    Next
    INDEX
    Explanations

    intelligence and capability

    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
    Stride
    -0.09
     dign
    -0.09
     chronic
    -0.09
     Mastery
    -0.09
     philosoph
    -0.09
     incompetent
    -0.09
    ãĢĢ ãĢĢ ãĢĢ ãĢĢ ãĢĢ
    -0.08
     γά
    -0.08
    çķª
    -0.08
    ampp
    -0.08
    POSITIVE LOGITS
     intelligence
    0.67
     Intelligence
    0.55
    intelligence
    0.51
     intelig
    0.45
     IQ
    0.41
    æĻº
    0.40
     smart
    0.40
     intellect
    0.39
     intelligent
    0.39
    æĻºèĥ½
    0.38
    Activations Density 0.217%

    No Known Activations