© 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. 43784
    Prev
    Next
    INDEX
    Explanations

    analyze and predict visitor behavior

    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
    mos
    -0.12
     inbound
    -0.10
    ÃŃny
    -0.10
    ÃŃc
    -0.09
    949
    -0.09
    Õ¡
    -0.09
     relev
    -0.09
    igers
    -0.08
    Portal
    -0.08
     Parkinson
    -0.08
    POSITIVE LOGITS
     visitors
    0.25
     visitor
    0.24
     Visitors
    0.18
     Visitor
    0.17
     session
    0.17
     site
    0.17
    bounce
    0.17
    visitor
    0.16
     visits
    0.16
     bounce
    0.16
    Activations Density 0.061%

    No Known Activations