© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43751
    Prev
    Next
    INDEX
    Explanations

    old, older, oldest

    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
     Cous
    -0.09
     Cousins
    -0.09
    adal
    -0.09
    妹
    -0.08
     nephew
    -0.08
    /current
    -0.08
     genders
    -0.08
     hvÄĽ
    -0.08
     grandson
    -0.08
     männer
    -0.08
    POSITIVE LOGITS
     older
    0.72
     old
    0.55
    older
    0.54
     Older
    0.54
    èĢģ
    0.46
     oldest
    0.45
     ÑģÑĤаÑĢ
    0.45
     elder
    0.43
     elderly
    0.43
     OLD
    0.38
    Activations Density 0.163%

    No Known Activations