© 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. 15017
    Prev
    Next
    INDEX
    Explanations

    reducing costs

    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
    IFI
    -0.10
    uess
    -0.10
    byss
    -0.10
    ghest
    -0.10
    ammen
    -0.09
    _Lean
    -0.09
     costly
    -0.09
    criptor
    -0.09
    eri
    -0.09
    /Dk
    -0.09
    POSITIVE LOGITS
    umer
    0.21
    liest
    0.20
    lier
    0.20
    umed
    0.17
     Rica
    0.17
    uming
    0.16
     associated
    0.15
    ed
    0.14
    -effective
    0.14
    liness
    0.14
    Activations Density 0.018%

    No Known Activations