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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 38220
    Prev
    Next
    INDEX
    Explanations

    Indonesian prices and currency if mentioned

    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
    habi
    -0.11
    exion
    -0.10
     Brook
    -0.10
     kami
    -0.10
    åĭĴ
    -0.10
     Jude
    -0.10
    jeta
    -0.10
     haz
    -0.09
     Osman
    -0.09
    jax
    -0.09
    POSITIVE LOGITS
     dan
    0.16
     Rp
    0.14
     Indonesia
    0.14
     Maul
    0.13
     Jakarta
    0.13
     Nug
    0.13
     Cah
    0.12
    itung
    0.12
     IDR
    0.12
     Indonesian
    0.12
    Activations Density 0.122%

    No Known Activations