© 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. 43256
    Prev
    Next
    INDEX
    Explanations

    swapping elements

    np_max-act · gemini-2.0-flash

    This neuron detects requests about exchanging or swapping two rows in a NumPy array.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    programming tasks and instructions related to manipulating data structures.

    oai_token-act-pair · gpt-4o-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
     на
    -0.07
     última
    -0.06
    _parts
    -0.06
     chặt
    -0.06
    (hwnd
    -0.06
     nắm
    -0.06
    AZ
    -0.06
     Shelter
    -0.06
     doGet
    -0.06
     mont
    -0.06
    POSITIVE LOGITS
    グ
    0.07
    -connected
    0.07
    ровер
    0.07
     artificially
    0.07
    ηση
    0.07
    -performance
    0.06
    么
    0.06
     修
    0.06
    Html
    0.06
     Волод
    0.06
    Activations Density 0.010%

    No Known Activations