© 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. 42205
    Prev
    Next
    INDEX
    Explanations

    physical actions and manipulation

    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
     chopping
    -0.12
    chner
    -0.11
    chwitz
    -0.10
     unloaded
    -0.09
    (Parse
    -0.09
     wiping
    -0.09
    dle
    -0.09
    obus
    -0.09
     shower
    -0.09
     padded
    -0.08
    POSITIVE LOGITS
     put
    0.13
     placed
    0.13
     carried
    0.12
     holding
    0.12
     carry
    0.12
     removed
    0.12
     Touch
    0.12
     remove
    0.11
     place
    0.11
     carrying
    0.11
    Activations Density 0.292%

    No Known Activations