© 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. 58421
    Prev
    Next
    INDEX
    Explanations

    expose or exposed

    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
    åĵ¡
    -0.10
    ALSE
    -0.09
    ucus
    -0.09
    alse
    -0.09
    fully
    -0.09
    ayne
    -0.09
     Bod
    -0.09
    estre
    -0.08
     Duy
    -0.08
    nod
    -0.08
    POSITIVE LOGITS
     kepada
    0.10
    éľ²
    0.10
    idon
    0.10
    URE
    0.10
     Zur
    0.10
     Exposure
    0.10
    iture
    0.09
    ToBounds
    0.09
    Exposed
    0.09
    sto
    0.09
    Activations Density 0.019%

    No Known Activations