© 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. 8679
    Prev
    Next
    INDEX
    Explanations

    help maintain

    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
     tim
    -0.09
     util
    -0.09
     succ
    -0.09
    wert
    -0.09
    Contain
    -0.08
    /fa
    -0.08
    ï¾ij
    -0.08
    éĢłæĪIJ
    -0.08
     overcoming
    -0.08
     stylist
    -0.08
    POSITIVE LOGITS
     maintaining
    0.21
     maintain
    0.20
    Maint
    0.19
    ç¶Ń
    0.18
     improve
    0.18
     mantener
    0.18
     promote
    0.18
     Maint
    0.18
    ç»´
    0.18
     improving
    0.17
    Activations Density 0.158%

    No Known Activations