© 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. 58550
    Prev
    Next
    INDEX
    Explanations

    environmental and social health

    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
     environmental
    -0.34
     Environmental
    -0.27
     environmentally
    -0.26
     environment
    -0.26
    _environment
    -0.26
    /environment
    -0.24
     Environment
    -0.24
    Environmental
    -0.24
    environment
    -0.23
    çݯå¢ĥ
    -0.21
    POSITIVE LOGITS
     health
    0.12
    enen
    0.10
    .health
    0.10
    avad
    0.10
     Health
    0.10
     human
    0.10
     cruelty
    0.09
    -health
    0.09
    ENER
    0.09
     Amerik
    0.09
    Activations Density 0.057%

    No Known Activations