© 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. 3913
    Prev
    Next
    INDEX
    Explanations

    fedora 37 sudo yum

    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
    ubuntu
    -0.18
    debian
    -0.18
     ubuntu
    -0.16
     debian
    -0.16
     Ubuntu
    -0.16
    Ubuntu
    -0.16
     Debian
    -0.15
     Ukrainian
    -0.13
    /ubuntu
    -0.12
     Ukrain
    -0.12
    POSITIVE LOGITS
    .rpm
    0.18
     fed
    0.17
     RPM
    0.17
     yum
    0.16
     rpm
    0.15
     koji
    0.15
     Red
    0.15
     rh
    0.15
     Fedora
    0.14
    .repo
    0.14
    Activations Density 0.037%

    No Known Activations