© 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. 49551
    Prev
    Next
    INDEX
    Explanations

    company has production capacity

    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
     Petroleum
    -0.10
    868
    -0.10
     petroleum
    -0.10
     passive
    -0.09
     Budget
    -0.09
    esus
    -0.09
     Pipeline
    -0.09
     duk
    -0.09
    aco
    -0.09
    _budget
    -0.09
    POSITIVE LOGITS
     plant
    0.21
     plants
    0.17
     production
    0.17
     capacity
    0.15
     output
    0.15
     raw
    0.15
     Plant
    0.14
     productions
    0.14
     captive
    0.12
     produced
    0.12
    Activations Density 0.069%

    No Known Activations