© 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. 14855
    Prev
    Next
    INDEX
    Explanations

    evaporation vapor diffusion

    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
    eum
    -0.10
    venge
    -0.09
     thaw
    -0.09
     Lump
    -0.09
     flushed
    -0.09
    heck
    -0.09
     Gund
    -0.08
     debris
    -0.08
    .scalablytyped
    -0.08
     deb
    -0.08
    POSITIVE LOGITS
     ev
    0.37
     cond
    0.28
     Ev
    0.25
    èĴ
    0.23
     mist
    0.22
     evapor
    0.22
    aporation
    0.22
     Cond
    0.20
    (ev
    0.20
    .ev
    0.20
    Activations Density 0.058%

    No Known Activations