© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92387
    Prev
    Next
    INDEX
    Explanations

    inline

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “inline” (and its variants like “inlined” or INLINE), i.e. references to function inlining.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tréal
    -0.08
     Việt
    -0.07
    ыт
    -0.07
     Ô
    -0.06
    иск
    -0.06
     comprehensive
    -0.06
    搜
    -0.06
    /*!↵
    -0.06
     악
    -0.06
     marks
    -0.06
    POSITIVE LOGITS
    .rooms
    0.06
    Integrated
    0.06
     sqlSession
    0.06
     converted
    0.06
    uitar
    0.06
    tarı
    0.06
    ो,
    0.06
     %
    0.06
    .Contracts
    0.06
    .hamcrest
    0.06
    Activations Density 0.003%

    No Known Activations