© 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. 63008
    Prev
    Next
    INDEX
    Explanations

    body parts and fluids

    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
     intestine
    -0.09
    çļ
    -0.09
    åĺ´
    -0.09
     rel
    -0.09
    :;\n
    -0.09
     Waist
    -0.09
     Strom
    -0.09
    eru
    -0.08
     mess
    -0.08
    _GF
    -0.08
    POSITIVE LOGITS
     veins
    0.27
     system
    0.22
     body
    0.21
     vein
    0.19
     bloodstream
    0.18
    ä½ĵ
    0.18
    ve
    0.18
     bodies
    0.18
    body
    0.17
     blood
    0.17
    Activations Density 0.030%

    No Known Activations