© 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. 52337
    Prev
    Next
    INDEX
    Explanations

    conspiracy agenda geoengineering

    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
     smugg
    -0.11
    oya
    -0.10
     vandal
    -0.09
    886
    -0.09
     sanct
    -0.09
    è¿·
    -0.09
     Charm
    -0.09
    olin
    -0.09
    charm
    -0.09
     Stall
    -0.08
    POSITIVE LOGITS
     Bilder
    0.21
     Agenda
    0.20
     bilder
    0.17
     Mason
    0.16
    agenda
    0.16
     conspir
    0.15
     Cab
    0.15
    bilder
    0.15
     Illum
    0.14
     agenda
    0.14
    Activations Density 0.063%

    No Known Activations