© 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. 12042
    Prev
    Next
    INDEX
    Explanations

    maintain or keep

    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
     Persistent
    -0.10
     restraint
    -0.09
    Stub
    -0.09
     Stub
    -0.09
     aud
    -0.08
    hiba
    -0.08
    KB
    -0.08
     afs
    -0.08
     kv
    -0.08
     persisted
    -0.08
    POSITIVE LOGITS
     maintain
    0.49
     keep
    0.48
    ä¿ĿæĮģ
    0.47
     maintaining
    0.42
     maint
    0.41
    Maint
    0.40
     mantener
    0.40
    ç»´
    0.40
     keeping
    0.40
    maint
    0.40
    Activations Density 0.149%

    No Known Activations