© 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. 58686
    Prev
    Next
    INDEX
    Explanations

    function definition arguments options

    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
    AdapterManager
    -0.09
     Forbes
    -0.09
     streak
    -0.09
    ObjectContext
    -0.09
     Camden
    -0.09
     Moff
    -0.09
    .sol
    -0.08
     gri
    -0.08
    _('
    -0.08
     Weaver
    -0.08
    POSITIVE LOGITS
     arguments
    0.18
     options
    0.17
    options
    0.17
    Options
    0.16
    _kwargs
    0.15
     parameters
    0.15
     Options
    0.15
    kwargs
    0.14
     Arguments
    0.14
     kwargs
    0.14
    Activations Density 0.076%

    No Known Activations