© 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. 27812
    Prev
    Next
    INDEX
    Explanations

    active in organizing or dedicated

    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
    Negative Logits
     ruling
    -0.10
     loyal
    -0.09
     ambitious
    -0.09
    èĥŀ
    -0.09
    ìłij
    -0.09
    xeb
    -0.08
    ifter
    -0.08
     instruct
    -0.08
    509
    -0.08
    azzo
    -0.08
    POSITIVE LOGITS
     fight
    0.29
     fights
    0.25
     Fight
    0.21
    fight
    0.21
     fighting
    0.20
    activ
    0.20
     Äijấu
    0.19
     fought
    0.19
    Fight
    0.19
     activ
    0.18
    Activations Density 0.084%

    No Known Activations