© 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. 61556
    Prev
    Next
    INDEX
    Explanations

    adding variety and excitement

    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
     intimidating
    -0.09
    udder
    -0.09
    illon
    -0.08
    iram
    -0.08
    ihan
    -0.08
     comfort
    -0.08
    veis
    -0.08
    nist
    -0.08
    ogan
    -0.08
    ï¾Ł
    -0.08
    POSITIVE LOGITS
     variety
    0.29
     Variety
    0.27
     spice
    0.25
     Spice
    0.22
     exciting
    0.22
     variation
    0.21
     excitement
    0.21
     diversity
    0.20
     fresh
    0.20
    Vari
    0.20
    Activations Density 0.133%

    No Known Activations