© 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. 37747
    Prev
    Next
    INDEX
    Explanations

    prevent, protect, limit

    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
     amel
    -0.13
     hur
    -0.10
     combating
    -0.10
     reconc
    -0.09
    é¾
    -0.09
     restraining
    -0.09
    OrNull
    -0.09
     refr
    -0.09
    ải
    -0.09
    æĪĴ
    -0.09
    POSITIVE LOGITS
     prevent
    0.24
     protect
    0.23
     protecting
    0.20
     prevented
    0.19
     Protect
    0.18
     prevents
    0.18
    ä¿ĿæĬ¤
    0.18
     limit
    0.17
     preventing
    0.17
     protects
    0.17
    Activations Density 0.070%

    No Known Activations