© 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. 48984
    Prev
    Next
    INDEX
    Explanations

    exposed to knowledge or experience

    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
    otec
    -0.09
    ToBounds
    -0.09
    VAS
    -0.09
    feb
    -0.08
    ;;;
    -0.08
     activeClassName
    -0.08
    Subscriber
    -0.08
     ÙħعÙĦ
    -0.08
     Aeros
    -0.08
    endas
    -0.08
    POSITIVE LOGITS
     exposure
    0.76
     Exposure
    0.66
     exposed
    0.59
     exposures
    0.50
     expose
    0.49
    Exposed
    0.47
     exposing
    0.41
     exposes
    0.41
    Expose
    0.40
    posure
    0.39
    Activations Density 0.185%

    No Known Activations