© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 44491
    Prev
    Next
    INDEX
    Explanations

    legs and core muscles

    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
     kne
    -0.12
     elbow
    -0.10
    amil
    -0.10
    åł
    -0.10
     knees
    -0.10
    oba
    -0.09
    eda
    -0.09
     Knee
    -0.09
    913
    -0.09
     itself
    -0.09
    POSITIVE LOGITS
     muscles
    0.20
     core
    0.18
    /core
    0.16
     Core
    0.16
     weak
    0.16
    (core
    0.15
     rot
    0.15
    core
    0.14
     gl
    0.14
    æł¸å¿ĥ
    0.14
    Activations Density 0.057%

    No Known Activations