© 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. 61591
    Prev
    Next
    INDEX
    Explanations

    rust-resistant primer

    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
     stained
    -0.13
     Plastic
    -0.11
    å¡ij
    -0.11
     Foam
    -0.10
     foam
    -0.10
     fabricated
    -0.09
     Fine
    -0.09
     staining
    -0.09
     Ble
    -0.09
     tissues
    -0.09
    POSITIVE LOGITS
     finish
    0.21
     coat
    0.20
    finish
    0.19
    coat
    0.18
     applied
    0.17
     coats
    0.17
     coating
    0.17
     primer
    0.16
     lac
    0.16
     layer
    0.15
    Activations Density 0.086%

    No Known Activations