© 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. 34868
    Prev
    Next
    INDEX
    Explanations

    ensure safety

    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
    Sdk
    -0.09
    Sus
    -0.09
     Sever
    -0.09
     nonatomic
    -0.09
     Sus
    -0.09
     Sv
    -0.09
    otal
    -0.08
    alus
    -0.08
     valueForKey
    -0.08
     Sylv
    -0.08
    POSITIVE LOGITS
     safe
    0.61
     safety
    0.60
    å®īåħ¨
    0.55
     safer
    0.52
     Safety
    0.48
     Safe
    0.46
    safe
    0.46
    -safe
    0.46
     safest
    0.46
     безопаÑģ
    0.46
    Activations Density 0.181%

    No Known Activations