© 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. 26265
    Prev
    Next
    INDEX
    Explanations

    living and lived

    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
     Lifecycle
    -0.09
     Survival
    -0.09
     Surv
    -0.09
    çĶŁåij½
    -0.09
     resting
    -0.09
     Bau
    -0.09
    teri
    -0.08
     Oliv
    -0.08
    Surv
    -0.08
    lop
    -0.08
    POSITIVE LOGITS
     living
    0.80
     lived
    0.70
    living
    0.63
     lives
    0.61
     live
    0.60
     Living
    0.56
     жив
    0.55
    Living
    0.53
     sá»ijng
    0.52
    live
    0.45
    Activations Density 0.280%

    No Known Activations