© 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. 59864
    Prev
    Next
    INDEX
    Explanations

    provides oxygen

    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
     bladder
    -0.10
    chk
    -0.09
     tub
    -0.09
     Tub
    -0.09
    ãĤ
    -0.09
     stomach
    -0.08
    avn
    -0.08
     trem
    -0.08
     (*((
    -0.08
    stry
    -0.08
    POSITIVE LOGITS
     blood
    0.33
     Blood
    0.28
    è¡Ģ
    0.27
    Blood
    0.26
    blood
    0.26
     oxygen
    0.23
     circulation
    0.21
     máu
    0.21
     supply
    0.20
     Oxygen
    0.20
    Activations Density 0.058%

    No Known Activations