© 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. 74614
    Prev
    Next
    INDEX
    Explanations

    statements

    np_max-act · gemini-2.0-flash

    This neuron detects finance-related terms, especially words about bank accounts and monitoring statements (e.g., “bank,” “statements,” “monitor,” “report”).

    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
    ابع
    -0.06
    　　　　　　　　　　　　　
    -0.06
     sale
    -0.06
    "On
    -0.06
     Size
    -0.06
     stall
    -0.06
     Emma
    -0.06
     роб
    -0.06
     Bazı
    -0.06
     beş
    -0.06
    POSITIVE LOGITS
    _IEnumerator
    0.07
    ордин
    0.07
     출연
    0.07
    .deepcopy
    0.06
    aze
    0.06
     sistem
    0.06
    antasy
    0.06
    -validate
    0.06
    ,),↵
    0.06
    lickr
    0.06
    Activations Density 0.014%

    No Known Activations