© 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. 592
    Prev
    Next
    INDEX
    Explanations

    discussing sensitive topics

    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
     expos
    -0.09
    ibal
    -0.09
    /cgi
    -0.08
     savage
    -0.08
    ëª
    -0.08
    üçük
    -0.08
    ProcessEvent
    -0.08
     mounts
    -0.08
    -sn
    -0.08
     Aerospace
    -0.08
    POSITIVE LOGITS
     sensitive
    0.39
     topic
    0.34
    -sensitive
    0.32
     topics
    0.31
    æķı
    0.30
    Sensitive
    0.30
     sensitivity
    0.28
     sensit
    0.27
    ensitive
    0.27
     Topic
    0.25
    Activations Density 0.152%

    No Known Activations