Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65159
    Prev
    Next
    INDEX
    Explanations

    country characteristics

    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
     flourishing
    -0.13
    .obtain
    -0.10
     Churchill
    -0.10
    urum
    -0.09
    illo
    -0.09
     Stark
    -0.09
    ï½Ŀ
    -0.09
     cham
    -0.09
    lore
    -0.09
    ponse
    -0.09
    POSITIVE LOGITS
     reputation
    0.19
     developed
    0.16
     reput
    0.15
     economy
    0.15
     Reputation
    0.13
     strong
    0.13
     Developed
    0.13
    develop
    0.12
     network
    0.11
     system
    0.11
    Activations Density 0.058%

    No Known Activations