© 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. 64184
    Prev
    Next
    INDEX
    Explanations

    waist and lower body

    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
     limbs
    -0.14
     limb
    -0.10
    çŃĭ
    -0.10
     tongues
    -0.10
     Legs
    -0.10
    uppen
    -0.09
     legs
    -0.09
    upe
    -0.09
     peg
    -0.09
    izoph
    -0.09
    POSITIVE LOGITS
     waist
    0.31
     Waist
    0.25
     knee
    0.21
    Wa
    0.19
    èħ°
    0.18
     Knee
    0.18
     hip
    0.17
    wa
    0.17
     mid
    0.17
     knees
    0.16
    Activations Density 0.072%

    No Known Activations