© 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. 37900
    Prev
    Next
    INDEX
    Explanations

    city names

    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
    áš
    -0.09
    defgroup
    -0.08
    .telegram
    -0.08
    GenerationStrategy
    -0.08
    ovny
    -0.08
     é¦
    -0.08
    ouser
    -0.08
    CTR
    -0.08
    isman
    -0.08
     reck
    -0.08
    POSITIVE LOGITS
    Ńå·ŀ
    0.18
    åı¤å±ĭ
    0.16
    ensburg
    0.14
    uttgart
    0.14
    ียà¸ĩà¹ĥหม
    0.14
    teborg
    0.13
    zhou
    0.13
    asbourg
    0.13
    derabad
    0.13
    apolis
    0.12
    Activations Density 0.208%

    No Known Activations