© 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. 34257
    Prev
    Next
    INDEX
    Explanations

    improvement and growth

    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
    enga
    -0.10
     consort
    -0.10
     ФедеÑĢаÑĨии
    -0.09
    ãģıãĤīãģĦ
    -0.09
    Ｖ
    -0.09
     Weston
    -0.09
    \tCopyright
    -0.08
    EditingStyle
    -0.08
    avad
    -0.08
     Austral
    -0.08
    POSITIVE LOGITS
     improvement
    0.36
     Improvement
    0.27
     improvements
    0.21
     improved
    0.20
     improve
    0.19
     growth
    0.17
    Impro
    0.17
     improving
    0.16
     miglior
    0.16
    æĶ¹
    0.15
    Activations Density 0.023%

    No Known Activations