© 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. 16619
    Prev
    Next
    INDEX
    Explanations

    violation or negative actions

    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
    Fault
    -0.10
     inconvenient
    -0.09
    .scalablytyped
    -0.09
     provoc
    -0.09
     身
    -0.09
    év
    -0.09
     Fault
    -0.09
    /***/
    -0.08
     wz
    -0.08
     Wend
    -0.08
    POSITIVE LOGITS
    è¿Ŀ
    0.29
     viol
    0.28
     violation
    0.26
    éģķ
    0.26
     contr
    0.25
     violate
    0.25
     Viol
    0.25
     infr
    0.25
     наÑĢÑĥÑĪ
    0.24
     violating
    0.23
    Activations Density 0.114%

    No Known Activations