© 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. 33401
    Prev
    Next
    INDEX
    Explanations

    alternatives and conjunctions

    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
     ende
    -0.09
     dedic
    -0.09
     Swing
    -0.09
     stores
    -0.09
     ways
    -0.08
    hist
    -0.08
    nameof
    -0.08
    ¶Į
    -0.08
     vign
    -0.08
    registers
    -0.08
    POSITIVE LOGITS
     action
    0.20
     interaction
    0.15
     activity
    0.15
    action
    0.14
     participation
    0.13
     involvement
    0.13
     response
    0.13
     contact
    0.13
     input
    0.12
     usage
    0.12
    Activations Density 0.326%

    No Known Activations