© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 64547
    Prev
    Next
    INDEX
    Explanations

    overthrow, coup, deposition

    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
    APPER
    -0.09
     Closure
    -0.09
     annihil
    -0.09
     closures
    -0.09
     closure
    -0.09
     outspoken
    -0.09
    IOD
    -0.09
    obl
    -0.09
     Discount
    -0.09
    263
    -0.09
    POSITIVE LOGITS
     topp
    0.27
     overthrow
    0.27
     ou
    0.24
     deposition
    0.22
     coup
    0.20
     removal
    0.20
     dep
    0.19
     removed
    0.18
     remove
    0.18
     depos
    0.18
    Activations Density 0.066%

    No Known Activations