© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 53348
    Prev
    Next
    INDEX
    Explanations

    MAC addresses in times

    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
    Negative Logits
    ervas
    -0.11
     Chin
    -0.10
     transfer
    -0.10
     transfers
    -0.10
    isp
    -0.10
     deflate
    -0.09
     Shaw
    -0.09
    Ipv
    -0.09
    _INET
    -0.09
     Fut
    -0.09
    POSITIVE LOGITS
     MAC
    0.24
    MAC
    0.22
    mac
    0.21
     mac
    0.20
    _MAC
    0.16
    .mac
    0.16
    (mac
    0.15
    Mac
    0.15
     Mac
    0.15
     frame
    0.15
    Activations Density 0.063%

    No Known Activations