© 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. 26468
    Prev
    Next
    INDEX
    Explanations

    gradual decline or increase

    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
    .Deep
    -0.08
    enever
    -0.08
     progressively
    -0.08
     wheel
    -0.08
     Carn
    -0.08
    issen
    -0.08
     Ames
    -0.08
     SHR
    -0.08
     wor
    -0.08
    uri
    -0.08
    POSITIVE LOGITS
     поÑģÑĤеп
    0.46
     slowly
    0.44
     gradual
    0.42
    æ¸IJ
    0.41
     dần
    0.39
    éĢIJ
    0.37
    grad
    0.37
     Grad
    0.36
     slow
    0.36
    æħ¢
    0.35
    Activations Density 0.276%

    No Known Activations