© 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. 21355
    Prev
    Next
    INDEX
    Explanations

    abandoned, burned, ruins

    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
     crippling
    -0.10
     nested
    -0.10
     crippled
    -0.10
     हल
    -0.09
     ripping
    -0.09
     injuring
    -0.09
    uba
    -0.08
    losing
    -0.08
     Bron
    -0.08
    inema
    -0.08
    POSITIVE LOGITS
     ruins
    0.32
     ru
    0.30
     ruin
    0.28
    ru
    0.27
     ÑĢÑĥ
    0.26
     Ru
    0.25
    Ru
    0.25
     destroyed
    0.23
     destruction
    0.23
    destroy
    0.21
    Activations Density 0.076%

    No Known Activations