© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 23900
    Prev
    Next
    INDEX
    Explanations

    advice to refrain or avoid

    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
     stamina
    -0.11
     Lat
    -0.10
     jog
    -0.10
    302
    -0.09
    egral
    -0.09
     Exercise
    -0.09
     exercise
    -0.09
    Exercise
    -0.09
    IDL
    -0.09
     exercised
    -0.09
    POSITIVE LOGITS
     taper
    0.18
     Training
    0.15
     training
    0.15
     recovery
    0.15
     Hanson
    0.14
    Training
    0.14
     tapered
    0.14
     race
    0.14
     runnable
    0.13
     injury
    0.13
    Activations Density 0.028%

    No Known Activations