© 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. 20973
    Prev
    Next
    INDEX
    Explanations

    long or lengthy

    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
    åĭĩ
    -0.10
    ØŃص
    -0.09
     dead
    -0.09
     excer
    -0.09
    -metadata
    -0.08
     widening
    -0.08
     nim
    -0.08
    Ø°
    -0.08
     concise
    -0.08
     haut
    -0.08
    POSITIVE LOGITS
     longer
    0.40
     lengthy
    0.31
     long
    0.31
     dÃłi
    0.30
     length
    0.29
    éķ¿
    0.28
     длин
    0.28
     Longer
    0.27
     uzun
    0.27
    éķ·
    0.27
    Activations Density 0.240%

    No Known Activations