© 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 (Instruct)
    5. 50-RESID-POST-GF
    7. 38661
    Prev
    Next
    INDEX
    Explanations

    AI language model

    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
    ster
    -0.09
     miniature
    -0.09
     rising
    -0.09
    eder
    -0.09
    ione
    -0.09
     batt
    -0.09
     watch
    -0.08
    ology
    -0.08
     Central
    -0.08
     expect
    -0.08
    POSITIVE LOGITS
    æĭŁ
    0.11
    329
    0.10
    ----------</
    0.09
    amespace
    0.09
    leground
    0.09
    âĢŀD
    0.09
    é¡ĺ
    0.08
    ctest
    0.08
     PVOID
    0.08
    æµľ
    0.08
    Activations Density 0.104%

    No Known Activations