© 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. 3702
    Prev
    Next
    INDEX
    Explanations

    proprietary platform

    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
     cheap
    -0.10
    .scalablytyped
    -0.10
     unlocked
    -0.09
     decentralized
    -0.09
     uninsured
    -0.09
     cruc
    -0.09
     lightweight
    -0.08
     cheaper
    -0.08
     Lightweight
    -0.08
     Programmer
    -0.08
    POSITIVE LOGITS
     proprietary
    0.34
     closed
    0.26
     commercial
    0.25
    propri
    0.22
    closed
    0.22
     Closed
    0.22
     Commercial
    0.21
    Closed
    0.20
     propri
    0.20
     propriet
    0.20
    Activations Density 0.100%

    No Known Activations