© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 590
    Prev
    Next
    INDEX
    Explanations

    holding office or power

    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
    mpar
    -0.08
     Electoral
    -0.08
    stad
    -0.08
    azor
    -0.08
    rink
    -0.08
    errar
    -0.08
     Stefan
    -0.08
    çĴĥ
    -0.08
    owler
    -0.08
     candidate
    -0.08
    POSITIVE LOGITS
     office
    0.61
    office
    0.45
     Office
    0.37
    -office
    0.35
    Office
    0.33
    _office
    0.33
     offices
    0.32
    .office
    0.31
    åĬŀåħ¬
    0.28
     úÅĻad
    0.24
    Activations Density 0.068%

    No Known Activations