© 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. 39207
    Prev
    Next
    INDEX
    Explanations

    have received, about one, Environmental Matters

    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
     collateral
    -0.09
     Bulls
    -0.09
    athon
    -0.09
    -âĢIJ
    -0.09
    ondon
    -0.09
     Ferry
    -0.09
     å
    -0.08
     Shan
    -0.08
    ози
    -0.08
    .chapter
    -0.08
    POSITIVE LOGITS
     cyber
    0.13
     material
    0.13
     Material
    0.11
    cy
    0.11
     registr
    0.11
     cybersecurity
    0.10
    ugin
    0.10
    Registr
    0.10
     ransom
    0.10
    Material
    0.09
    Activations Density 0.012%

    No Known Activations