© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 53235
    Prev
    Next
    INDEX
    Explanations

    manifest in your life

    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
    Negative Logits
     Gast
    -0.10
     Jad
    -0.10
    cp
    -0.10
     veniam
    -0.09
     ragaz
    -0.09
    lain
    -0.09
     Garr
    -0.09
    mana
    -0.09
    adel
    -0.09
    iteral
    -0.09
    POSITIVE LOGITS
    à¹ĥà¸Ļà¸Ĭ
    0.18
     enter
    0.17
     enters
    0.16
     lives
    0.16
     entered
    0.16
     vÃło
    0.15
     into
    0.15
    åħ¥
    0.14
     ÙĪارد
    0.14
     Into
    0.13
    Activations Density 0.106%

    No Known Activations