© 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. 40036
    Prev
    Next
    INDEX
    Explanations

    consulting and support services

    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
     industry
    -0.14
    industry
    -0.12
    Industry
    -0.10
     company
    -0.10
     industries
    -0.10
     firms
    -0.09
    ãĤŀ
    -0.09
     companies
    -0.09
    è¡Įä¸ļ
    -0.09
    Companies
    -0.09
    POSITIVE LOGITS
     consulting
    0.17
     services
    0.17
     solutions
    0.15
     Consulting
    0.14
     turn
    0.14
     training
    0.13
     Services
    0.12
     consultation
    0.12
     ÑĥÑģлÑĥг
    0.12
    Consult
    0.11
    Activations Density 0.098%

    No Known Activations