© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 44463
    Prev
    Next
    INDEX
    Explanations

    intelligent and

    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
     intelligence
    -0.23
     intellect
    -0.22
     intelligent
    -0.21
     intellectual
    -0.17
     Intelligence
    -0.16
     intellectually
    -0.15
    intelligence
    -0.15
     Intelligent
    -0.15
     brains
    -0.15
     intelig
    -0.15
    POSITIVE LOGITS
     decis
    0.10
     Insider
    0.10
    ibe
    0.10
     Edmund
    0.10
     perception
    0.09
    ucks
    0.09
    Sou
    0.09
    urve
    0.09
    uchar
    0.09
     emotional
    0.09
    Activations Density 0.084%

    No Known Activations