© 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. 38205
    Prev
    Next
    INDEX
    Explanations

    standing by no matter what

    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
     collaps
    -0.09
    átka
    -0.09
     unre
    -0.09
    ursed
    -0.08
     horn
    -0.08
     handed
    -0.08
    akat
    -0.08
    alem
    -0.08
    SEG
    -0.08
     uncert
    -0.08
    POSITIVE LOGITS
     loyalty
    0.25
    loy
    0.23
     loyal
    0.22
     Loy
    0.22
    LOY
    0.18
     backs
    0.15
     stick
    0.15
     support
    0.15
     Stick
    0.15
     defend
    0.14
    Activations Density 0.050%

    No Known Activations