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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 34929
    Prev
    Next
    INDEX
    Explanations

    common sense intuition

    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
     hypoth
    -0.12
    ottage
    -0.11
     conject
    -0.10
    934
    -0.09
     resign
    -0.09
     wholesale
    -0.09
     hypotheses
    -0.09
     hypothetical
    -0.08
    ivel
    -0.08
     ãĥ¼
    -0.08
    POSITIVE LOGITS
     common
    0.29
     commons
    0.27
    commons
    0.23
    common
    0.23
     natural
    0.20
     Common
    0.20
     Commons
    0.20
    -common
    0.20
     gut
    0.20
    Common
    0.20
    Activations Density 0.167%

    No Known Activations