© 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. 3878
    Prev
    Next
    INDEX
    Explanations

    what is the direction

    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
     timelines
    -0.09
    ï¾
    -0.09
    ILI
    -0.09
    asca
    -0.09
    aldi
    -0.09
     Lage
    -0.08
    obel
    -0.08
     situation
    -0.08
     ticks
    -0.08
    ioned
    -0.08
    POSITIVE LOGITS
     angle
    0.41
     direction
    0.35
     angles
    0.32
    angle
    0.31
     focus
    0.27
     Angle
    0.27
    æĸ¹åIJij
    0.27
    è§Ĵ
    0.26
    direction
    0.26
    Angle
    0.25
    Activations Density 0.222%

    No Known Activations