© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 124187
    Prev
    Next
    INDEX
    Explanations

    await

    np_max-act · gemini-2.0-flash

    code snippets and descriptions related to asynchronous programming and event handling in JavaScript.

    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
     concentrating
    -0.08
     Theme
    -0.07
    finger
    -0.07
     Sending
    -0.07
     Labels
    -0.07
     максим
    -0.07
     klas
    -0.06
     KDE
    -0.06
     star
    -0.06
     Max
    -0.06
    POSITIVE LOGITS
     awaiting
    0.10
    Await
    0.08
     await
    0.08
    await
    0.08
     Await
    0.08
     awaited
    0.07
    .await
    0.07
    	await
    0.07
    .setRotation
    0.06
     Audrey
    0.06
    Activations Density 0.003%

    No Known Activations