© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 44191
    Prev
    Next
    INDEX
    Explanations

    energy consumption and well-being

    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
    tainment
    -0.10
     velocities
    -0.09
     veloc
    -0.09
     Uhr
    -0.08
    stored
    -0.08
     Lump
    -0.08
    ewan
    -0.08
     Durant
    -0.08
    ｨ
    -0.08
    illon
    -0.08
    POSITIVE LOGITS
     energy
    0.57
    energy
    0.43
     Energy
    0.41
    Energy
    0.38
    -energy
    0.35
     consumption
    0.35
    _energy
    0.34
     fuel
    0.32
     consume
    0.32
    .energy
    0.32
    Activations Density 0.128%

    No Known Activations