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

    Neuronpedia

    Jacobian LensNEW
    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. 56654
    Prev
    Next
    INDEX
    Explanations

    payments and credit cards

    np_max-act · gemini-2.0-flash

    The neuron detects references to payment, especially headings or mentions of payment methods (e.g., credit cards, PayPal).

    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
    орів
    -0.06
    ../../../../
    -0.06
     後
    -0.06
     Igor
    -0.06
    や
    -0.06
     мінім
    -0.06
     outputs
    -0.06
    ustos
    -0.06
    ()));
↵
    -0.06
     pasture
    -0.06
    POSITIVE LOGITS
     fortunately
    0.07
    тех
    0.07
    DK
    0.06
    �
    0.06
     disagrees
    0.06
    destruct
    0.06
    -next
    0.06
     Book
    0.06
    최
    0.06
     Keeper
    0.06
    Activations Density 0.014%

    No Known Activations