© 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. 5477
    Prev
    Next
    INDEX
    Explanations

    email deliverability and blocking

    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
     Http
    -0.11
     Firewall
    -0.10
     mailed
    -0.10
     Epic
    -0.09
     Telegram
    -0.09
     VPN
    -0.09
    .telegram
    -0.09
    PN
    -0.09
     mails
    -0.09
     mailing
    -0.09
    POSITIVE LOGITS
     DK
    0.19
    bounce
    0.18
     SPF
    0.18
     MX
    0.18
     bounce
    0.17
    DK
    0.16
     Domain
    0.15
     domain
    0.15
     bounced
    0.15
    MX
    0.15
    Activations Density 0.044%

    No Known Activations