© 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. 37878
    Prev
    Next
    INDEX
    Explanations

    finance

    np_max-act · gemini-2.0-flash

    financial products and promotional offers related to installment payments.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects mentions of financing or payment‐plan terms, especially interest‐free or installment offers.

    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
    IAN
    -0.07
     Gardner
    -0.07
    mít
    -0.07
     unbe
    -0.07
     Rover
    -0.07
    296
    -0.06
     Bee
    -0.06
    	back
    -0.06
     Liebe
    -0.06
     Execution
    -0.06
    POSITIVE LOGITS
     damaged
    0.06
     dob
    0.06
    ルフ
    0.06
    velocity
    0.06
    ruby
    0.06
     město
    0.06
     dům
    0.06
     alloys
    0.06
    mysql
    0.06
     özel
    0.06
    Activations Density 0.014%

    No Known Activations