© 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. 60276
    Prev
    Next
    INDEX
    Explanations

    by the local organizers

    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
     diplomatic
    -0.10
    âīł
    -0.10
     Dipl
    -0.10
     diplom
    -0.09
    -0.09
     Auditor
    -0.09
     sarcast
    -0.09
     Presidents
    -0.09
     invariant
    -0.09
     sal
    -0.08
    POSITIVE LOGITS
     authorities
    0.40
     Authorities
    0.26
     authority
    0.24
    Authorities
    0.24
     powers
    0.24
     officials
    0.19
     administration
    0.17
     влаÑģÑĤи
    0.17
     Powers
    0.17
     committee
    0.17
    Activations Density 0.160%

    No Known Activations