© 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. 9245
    Prev
    Next
    INDEX
    Explanations

    efficiently process information

    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
     immedi
    -0.10
     responsibly
    -0.10
     Helpful
    -0.10
     Seamless
    -0.09
     Immediate
    -0.09
     immediate
    -0.09
    Strict
    -0.09
    wyn
    -0.09
    .volley
    -0.09
     Glover
    -0.09
    POSITIVE LOGITS
    åĬ¹
    0.27
     efficient
    0.26
     efficiency
    0.26
    efficient
    0.26
     cheap
    0.25
     effic
    0.25
     íļ¨
    0.24
     ÑįÑĦÑĦекÑĤив
    0.24
     efficiently
    0.24
     hiá»ĩu
    0.23
    Activations Density 0.249%

    No Known Activations