© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 1560
    Prev
    Next
    INDEX
    Explanations

    power rack

    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
    uran
    -0.10
     quart
    -0.09
    ouse
    -0.09
     lup
    -0.09
     packaging
    -0.09
     å§
    -0.09
     bedrooms
    -0.09
    ãĤĿ
    -0.09
    clide
    -0.08
     æ¯
    -0.08
    POSITIVE LOGITS
     floor
    0.15
     bay
    0.14
     seismic
    0.13
    ais
    0.12
     space
    0.12
     layout
    0.12
     island
    0.11
     partition
    0.11
     fork
    0.11
     footprint
    0.11
    Activations Density 0.056%

    No Known Activations