© 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. 53244
    Prev
    Next
    INDEX
    Explanations

    air defense, vapor diffusion, service establishment, safety regulations

    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
     ins
    -0.08
    @nate
    -0.08
    cel
    -0.08
    cház
    -0.08
     strapon
    -0.08
    anja
    -0.08
    è¥
    -0.08
    riel
    -0.08
    odzi
    -0.08
    raph
    -0.08
    POSITIVE LOGITS
    ingly
    0.10
    eps
    0.10
    iores
    0.10
    sth
    0.09
    age
    0.09
     cref
    0.09
    /g
    0.08
     eskort
    0.08
    avl
    0.08
    lain
    0.08
    Activations Density 0.394%

    No Known Activations