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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33602
    Prev
    Next
    INDEX
    Explanations

    the villagers, town, forest

    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
     cities
    -0.15
     Cities
    -0.14
    cities
    -0.13
    Cities
    -0.12
    éĥ½å¸Ĥ
    -0.11
     homeless
    -0.10
     provinces
    -0.10
     Zoo
    -0.10
     malls
    -0.10
    camel
    -0.10
    POSITIVE LOGITS
     village
    0.25
     town
    0.21
     villagers
    0.21
     mayor
    0.20
    æĿij
    0.19
     Village
    0.19
     Mayor
    0.19
    Mayor
    0.18
     community
    0.16
    illage
    0.16
    Activations Density 0.096%

    No Known Activations