© 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. 21247
    Prev
    Next
    INDEX
    Explanations

    political cooperation and compromise

    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
    ;;;;;;;;
    -0.10
    éĶ¦
    -0.09
     concerted
    -0.09
     Jad
    -0.09
     downt
    -0.08
    esini
    -0.08
     hopes
    -0.08
    .ex
    -0.08
     expressive
    -0.08
     coup
    -0.08
    POSITIVE LOGITS
     commitment
    0.20
     leadership
    0.17
     political
    0.16
     willing
    0.16
     action
    0.16
     committed
    0.15
     Commit
    0.15
     willingness
    0.15
     Leadership
    0.14
     resolve
    0.14
    Activations Density 0.047%

    No Known Activations