© 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. 35376
    Prev
    Next
    INDEX
    Explanations

    wise old

    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
    _hero
    -0.09
    çıį
    -0.09
     nave
    -0.09
     tint
    -0.09
    urses
    -0.09
    nave
    -0.08
     accountant
    -0.08
     innoc
    -0.08
     nob
    -0.08
     ne
    -0.08
    POSITIVE LOGITS
     wise
    0.29
     Wise
    0.24
     sage
    0.21
    wise
    0.21
    -wise
    0.21
     elderly
    0.20
    sage
    0.17
     old
    0.16
     wis
    0.16
    èĢģ
    0.16
    Activations Density 0.174%

    No Known Activations