© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 61637
    Prev
    Next
    INDEX
    Explanations

    HFN Merger/Risk Arbitrage Index funds

    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
     grooming
    -0.10
     tid
    -0.10
    ervas
    -0.10
    asca
    -0.09
    ingo
    -0.09
    oxel
    -0.09
    CSR
    -0.09
    uxe
    -0.09
    èĤ¡ä»½
    -0.09
     cum
    -0.09
    POSITIVE LOGITS
     manager
    0.18
     fund
    0.16
     managers
    0.15
     hedge
    0.13
     Tactical
    0.13
     Managers
    0.13
    -manager
    0.13
    manager
    0.13
     uncon
    0.12
    mgr
    0.12
    Activations Density 0.061%

    No Known Activations