© 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. 11513
    Prev
    Next
    INDEX
    Explanations

    Objectives, Abstractive, Micro-enterprises

    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
    ÌĨ
    -0.09
    stery
    -0.08
     eff
    -0.08
    Ìī
    -0.08
     Vig
    -0.08
     strSQL
    -0.08
    .vertx
    -0.08
     BITTE
    -0.07
    :ï½ī
    -0.07
    eneric
    -0.07
    POSITIVE LOGITS
     section
    0.10
    tam
    0.08
    hots
    0.08
     imperson
    0.08
     tam
    0.08
    ****
    0.08
    olley
    0.08
     zoom
    0.08
     promot
    0.08
     Fucked
    0.08
    Activations Density 0.088%

    No Known Activations