Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43558
    Prev
    Next
    INDEX
    Explanations

    exchange rate

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of foreign‐currency exchange—terms like “exchange rates,” “conversion,” and services such as “TransferWise/Borderless.”

    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
    	Il
    -0.07
     Photographer
    -0.06
     charisma
    -0.06
     mile
    -0.06
    ่ง
    -0.06
    .Buttons
    -0.06
     кноп
    -0.06
     dishwasher
    -0.06
    町
    -0.06
     Agricultural
    -0.06
    POSITIVE LOGITS
     semantics
    0.07
    _change
    0.07
    timeline
    0.07
     immutable
    0.07
    asset
    0.06
     WW
    0.06
     USERS
    0.06
    transform
    0.06
    (","
    0.06
     fib
    0.06
    Activations Density 0.008%

    No Known Activations