© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 37884
    Prev
    Next
    INDEX
    Explanations

    cost reduction and profit increase

    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
     costs
    -0.23
     Costs
    -0.19
     costly
    -0.19
    _costs
    -0.17
     kosten
    -0.16
     costa
    -0.15
     costo
    -0.15
    æĪIJæľ¬
    -0.14
     expensive
    -0.13
     costing
    -0.13
    POSITIVE LOGITS
     revenue
    0.13
     Complexity
    0.10
     revenues
    0.10
     complexity
    0.10
     labour
    0.10
    elly
    0.10
     Revenue
    0.10
     Conway
    0.10
     effort
    0.10
    icher
    0.09
    Activations Density 0.032%

    No Known Activations