© 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. 56958
    Prev
    Next
    INDEX
    Explanations

    mercury vaccine fabrication

    np_acts-logits-general · gemini-2.5-flash-lite

    Spanish language text, particularly scientific or technical passages about natural substances and materials.

    oai_token-act-pair · claude-4-5-haikuTriggered by @yooniel31
    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
    ream
    -0.10
     McMaster
    -0.10
    ç£
    -0.10
     Zuk
    -0.09
     Punch
    -0.09
     Hercules
    -0.09
     Yorkshire
    -0.09
     Tata
    -0.08
    donnees
    -0.08
     CO
    -0.08
    POSITIVE LOGITS
     Mercury
    0.35
     mercury
    0.34
    Mer
    0.28
     Mer
    0.23
     mer
    0.22
    cury
    0.22
    mer
    0.19
     amalg
    0.18
     меÑĢ
    0.17
     Merc
    0.16
    Activations Density 0.036%

    No Known Activations