© 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. 8797
    Prev
    Next
    INDEX
    Explanations

    chest and rib descriptions

    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
     ankle
    -0.12
    rear
    -0.11
     Rear
    -0.11
    èħ¿
    -0.11
     leg
    -0.10
    èĢ³
    -0.10
     rear
    -0.10
    ï¾Ł
    -0.10
     thigh
    -0.10
     cerebral
    -0.09
    POSITIVE LOGITS
     chest
    0.49
     Chest
    0.42
    chest
    0.38
     chests
    0.36
    èĥ¸
    0.33
     ribs
    0.28
     rib
    0.27
     breast
    0.25
     Rib
    0.25
     thor
    0.25
    Activations Density 0.059%

    No Known Activations