© 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. 42413
    Prev
    Next
    INDEX
    Explanations

    back and shoulders

    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
     belly
    -0.10
     Belly
    -0.10
     limb
    -0.10
     pants
    -0.10
     toe
    -0.09
    isman
    -0.09
     tongue
    -0.09
    elix
    -0.09
    RV
    -0.09
    pants
    -0.09
    POSITIVE LOGITS
     backs
    0.60
     shoulders
    0.51
    èĥĮ
    0.49
     shoulder
    0.42
    backs
    0.39
    èĤ©
    0.38
     Shoulder
    0.35
     back
    0.34
    back
    0.33
    -back
    0.33
    Activations Density 0.052%

    No Known Activations