© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 26088
    Prev
    Next
    INDEX
    Explanations

    offensive or harmful to others

    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
     showToast
    -0.09
    eron
    -0.08
     matching
    -0.08
     Matching
    -0.08
     Wizard
    -0.08
    èŃ
    -0.08
     adverse
    -0.08
     uÄŁ
    -0.08
    Matching
    -0.08
    abbage
    -0.08
    POSITIVE LOGITS
     kepada
    0.22
     towards
    0.14
     others
    0.14
    others
    0.12
     nature
    0.12
     toward
    0.11
    Others
    0.11
     Others
    0.11
     to
    0.11
    ingo
    0.10
    Activations Density 0.060%

    No Known Activations