© 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. 34753
    Prev
    Next
    INDEX
    Explanations

    addresses and math calculations

    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
     Kern
    -0.08
    ebek
    -0.07
     UIScreen
    -0.07
     köln
    -0.07
    ekli
    -0.07
    TestFixture
    -0.07
    PyObject
    -0.07
    illion
    -0.07
     münchen
    -0.07
    tractor
    -0.07
    POSITIVE LOGITS
    /*č\n
    0.08
     inher
    0.07
     konkrét
    0.07
    _SUITE
    0.07
    Tweet
    0.07
    ฯ
    0.07
    CoreApplication
    0.07
     inter
    0.07
    hend
    0.07
     sice
    0.07
    Activations Density 0.645%

    No Known Activations