© 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. 54203
    Prev
    Next
    INDEX
    Explanations

    filling scratches with a special tool

    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
     Crate
    -0.10
     surface
    -0.10
     Hubb
    -0.10
     worm
    -0.09
     moll
    -0.09
    surface
    -0.09
    errated
    -0.09
     surfaces
    -0.09
    splash
    -0.09
    steel
    -0.09
    POSITIVE LOGITS
    -filled
    0.14
     transparent
    0.11
     sealed
    0.11
    atrix
    0.11
     glass
    0.11
     filled
    0.10
     Sandwich
    0.10
     wicked
    0.10
     lod
    0.10
    çİ»çĴĥ
    0.10
    Activations Density 0.074%

    No Known Activations