© 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. 49645
    Prev
    Next
    INDEX
    Explanations

    agility and quick reflexes

    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
     strut
    -0.09
    etur
    -0.09
    ONGL
    -0.08
    amet
    -0.08
     Km
    -0.08
    marshall
    -0.08
    ｡
    -0.08
     Trem
    -0.08
    alyzer
    -0.08
    alph
    -0.08
    POSITIVE LOGITS
     nim
    0.25
     agility
    0.22
     agile
    0.22
    æķı
    0.22
     quick
    0.21
    nim
    0.21
     Nim
    0.19
     Agile
    0.19
     movements
    0.18
     dod
    0.17
    Activations Density 0.071%

    No Known Activations