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. 44837
    Prev
    Next
    INDEX
    Explanations

    regions and states

    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
     Canada
    -0.13
    Canada
    -0.11
     Canadians
    -0.10
     Canadian
    -0.10
     canada
    -0.10
    USA
    -0.10
     towns
    -0.10
     Provincial
    -0.10
     Lanka
    -0.10
     provincial
    -0.09
    POSITIVE LOGITS
     Lomb
    0.21
     Trent
    0.13
    orraine
    0.13
     Catalonia
    0.12
    azio
    0.12
     Als
    0.12
     Karnataka
    0.12
     Sax
    0.12
     Bret
    0.12
     Kurdistan
    0.12
    Activations Density 0.132%

    No Known Activations