© 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. 58636
    Prev
    Next
    INDEX
    Explanations

    GDP growth

    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
     fraction
    -0.09
    aki
    -0.09
    llx
    -0.08
    kovi
    -0.08
     Gauss
    -0.08
    abar
    -0.08
    fluence
    -0.08
    ï¿£ï½Ģ
    -0.08
     Oliv
    -0.08
     Mej
    -0.08
    POSITIVE LOGITS
     growth
    0.30
     compound
    0.29
     Compound
    0.27
     Growth
    0.26
    compound
    0.24
    Compound
    0.24
    growth
    0.22
     rate
    0.22
    _growth
    0.21
     grow
    0.19
    Activations Density 0.064%

    No Known Activations