© 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. 15584
    Prev
    Next
    INDEX
    Explanations

    world is described

    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
     sint
    -0.09
    chter
    -0.09
    elop
    -0.09
    tered
    -0.09
     decltype
    -0.09
     unearth
    -0.09
    aus
    -0.09
    chied
    -0.09
     prolifer
    -0.08
    hibited
    -0.08
    POSITIVE LOGITS
     vast
    0.15
     governed
    0.12
    flat
    0.12
     govern
    0.12
     flat
    0.12
     harsh
    0.11
     Bret
    0.11
     Govern
    0.11
    大ãģį
    0.11
     ours
    0.10
    Activations Density 0.076%

    No Known Activations