© 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. 20710
    Prev
    Next
    INDEX
    Explanations

    holy, sacred, divine

    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
     Gods
    -0.11
     fare
    -0.10
    315
    -0.09
    moz
    -0.09
    cj
    -0.09
    ares
    -0.08
    /column
    -0.08
    icit
    -0.08
     gods
    -0.08
     sheer
    -0.08
    POSITIVE LOGITS
    otal
    0.14
     cow
    0.14
    /sec
    0.13
     Cow
    0.13
     intervention
    0.12
     cows
    0.12
    okes
    0.11
     feminine
    0.11
     beings
    0.11
     Intervention
    0.11
    Activations Density 0.038%

    No Known Activations