© 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. 38127
    Prev
    Next
    INDEX
    Explanations

    print and variable assignment

    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
    .TryParse
    -0.09
     kak
    -0.09
    коÑĢиÑģÑĤ
    -0.08
    opia
    -0.08
     pseud
    -0.08
    @Id
    -0.08
    finder
    -0.08
    Objects
    -0.08
     Hab
    -0.08
    âĢIJâĢIJ
    -0.08
    POSITIVE LOGITS
     print
    0.37
    print
    0.32
     println
    0.27
    println
    0.23
    \tprint
    0.23
     printf
    0.23
     cout
    0.20
    .print
    0.20
     console
    0.19
     Print
    0.19
    Activations Density 0.040%

    No Known Activations