© 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. 30028
    Prev
    Next
    INDEX
    Explanations

    legal framework and agreements

    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
    aze
    -0.12
    ục
    -0.10
     Garland
    -0.09
    antro
    -0.09
    ç©´
    -0.09
    andas
    -0.08
     census
    -0.08
    dea
    -0.08
    zilla
    -0.08
    case
    -0.08
    POSITIVE LOGITS
     instrument
    0.24
     document
    0.20
     tool
    0.17
     instruments
    0.16
     basis
    0.16
     framework
    0.16
     documento
    0.16
     vehicle
    0.16
     guide
    0.16
    binding
    0.14
    Activations Density 0.072%

    No Known Activations