© 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. 40979
    Prev
    Next
    INDEX
    Explanations

    computer operations, virus, controlled, monitors, network, systems

    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
     Computing
    -0.11
    PTY
    -0.10
    TOOLS
    -0.09
     Rav
    -0.09
    apore
    -0.09
    istrovstvÃŃ
    -0.09
     Tanner
    -0.09
     Witt
    -0.09
    urious
    -0.08
     Garr
    -0.08
    POSITIVE LOGITS
    ized
    0.32
    ised
    0.23
    ization
    0.18
    IZED
    0.17
    ize
    0.17
    izing
    0.16
    íĵ¨íĦ°
    0.16
    ISED
    0.15
    isation
    0.14
     bảng
    0.14
    Activations Density 0.041%

    No Known Activations