© 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. 43448
    Prev
    Next
    INDEX
    Explanations

    health and risks

    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
    ollo
    -0.10
    782
    -0.09
    (åľŁ
    -0.09
    mage
    -0.08
     stre
    -0.08
    iston
    -0.08
     hn
    -0.08
    .databinding
    -0.08
    ÙĬدة
    -0.08
    ymb
    -0.08
    POSITIVE LOGITS
     concerns
    0.16
     direct
    0.15
     human
    0.15
     individual
    0.15
     risks
    0.14
     personal
    0.13
     concern
    0.13
     physical
    0.13
     immediate
    0.13
     health
    0.12
    Activations Density 0.006%

    No Known Activations