© 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. 21798
    Prev
    Next
    INDEX
    Explanations

    causing harm or injury

    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
    tsy
    -0.09
     поÑĢаж
    -0.09
    _acl
    -0.09
     inev
    -0.08
    ILON
    -0.08
     Wilkinson
    -0.08
     HDC
    -0.08
    .Errors
    -0.08
    IRQ
    -0.08
     далеко
    -0.08
    POSITIVE LOGITS
     harm
    0.66
     Harm
    0.51
     injury
    0.41
     hurt
    0.38
     harmed
    0.37
     harms
    0.34
     damage
    0.34
     Injury
    0.33
     вÑĢед
    0.31
     harming
    0.29
    Activations Density 0.085%

    No Known Activations