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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 125933
    Prev
    Next
    INDEX
    Explanations

    incentives and concessions

    np_max-act · gemini-2.0-flash

    This neuron responds to terms about monetary incentives or payments (e.g., money, offer, incentives, discounts, gifts, kickbacks).

    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
    .ut
    -0.07
     един
    -0.06
    �
    -0.06
     Trey
    -0.06
    '''↵
    -0.06
    461
    -0.06
     Ukrainian
    -0.06
    asu
    -0.06
     praž
    -0.06
     команд
    -0.06
    POSITIVE LOGITS
    킬
    0.07
    DataSource
    0.06
    	class
    0.06
     силь
    0.06
     seeded
    0.06
     dez
    0.06
    ござ
    0.06
    .GetAsync
    0.06
    못
    0.06
     příležit
    0.06
    Activations Density 0.039%

    No Known Activations