© 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. 13153
    Prev
    Next
    INDEX
    Explanations

    fuel and oxidizer

    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
     airl
    -0.11
     franch
    -0.09
    rial
    -0.09
     airborne
    -0.09
     fet
    -0.09
     planes
    -0.09
    _INTR
    -0.09
    velt
    -0.09
     compound
    -0.09
     tire
    -0.09
    POSITIVE LOGITS
     prop
    0.20
     gim
    0.17
     thrust
    0.16
     rocket
    0.15
     thr
    0.15
     throat
    0.15
    ellant
    0.15
     Thr
    0.15
     ÑĤÑı
    0.15
    Rocket
    0.14
    Activations Density 0.016%

    No Known Activations