© 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. 2087
    Prev
    Next
    INDEX
    Explanations

    maintain homeostasis

    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
    ï¿£ï½Ģ
    -0.11
    zier
    -0.10
    verb
    -0.09
     mitochond
    -0.09
    IOC
    -0.09
     mim
    -0.09
    lien
    -0.09
     maximum
    -0.09
    ddl
    -0.09
    ERP
    -0.09
    POSITIVE LOGITS
     balance
    0.22
     home
    0.19
    æģĴ
    0.18
     Balance
    0.18
    balance
    0.17
    alance
    0.15
    home
    0.15
    Balance
    0.15
     pH
    0.15
     maintain
    0.14
    Activations Density 0.039%

    No Known Activations