© 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. 40149
    Prev
    Next
    INDEX
    Explanations

    gradient

    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
     tangent
    -0.10
     parity
    -0.10
     progressively
    -0.09
     Gund
    -0.09
     lowered
    -0.09
    igue
    -0.09
     figure
    -0.09
    lement
    -0.09
    elay
    -0.08
     loops
    -0.08
    POSITIVE LOGITS
     grad
    0.31
     gradient
    0.31
    æ¸IJ
    0.25
     gradients
    0.24
    Grad
    0.24
    grad
    0.24
     Grad
    0.23
    gradient
    0.23
     graduation
    0.23
     Gradient
    0.23
    Activations Density 0.145%

    No Known Activations