© 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. 34723
    Prev
    Next
    INDEX
    Explanations

    state machine or api struct init

    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
     cout
    -0.12
     typeid
    -0.11
    UDA
    -0.10
    cout
    -0.10
    CppType
    -0.10
    printStats
    -0.10
    /***************************************************************************\n
    -0.10
    ë¹ĦìķĦ
    -0.09
     Cout
    -0.09
    [,]
    -0.09
    POSITIVE LOGITS
     NULL
    0.15
    ->
    0.13
    =NULL
    0.12
    NULL
    0.12
     free
    0.12
    (NULL
    0.11
     ret
    0.11
     opaque
    0.11
     *
    0.11
    uth
    0.11
    Activations Density 0.081%

    No Known Activations