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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 44278
    Prev
    Next
    INDEX
    Explanations

    determiners and articles

    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
     assistir
    -0.10
    ">//
    -0.09
    _SA
    -0.09
     massaggi
    -0.09
    /Documents
    -0.08
     siguientes
    -0.08
    iff
    -0.08
    pie
    -0.08
     prostitutas
    -0.08
     meille
    -0.08
    POSITIVE LOGITS
    ä¸Ģ个
    0.15
     eine
    0.14
     una
    0.14
     uma
    0.13
    ä¸ĢåĢĭ
    0.13
     einen
    0.12
    ä¸Ģç§į
    0.12
     serialVersionUID
    0.11
     sebuah
    0.11
     een
    0.11
    Activations Density 0.178%

    No Known Activations