© 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. 9215
    Prev
    Next
    INDEX
    Explanations

    loyalty/rewards

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of loyalty or rewards programs (e.g. words like loyalty, programme/fidélité, points, rewards).

    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
     Paginator
    -0.07
     pore
    -0.07
     servicios
    -0.06
    stdbool
    -0.06
    鑑
    -0.06
    .WRAP
    -0.06
    *)&
    -0.06
     včetně
    -0.06
    locking
    -0.06
     yans
    -0.06
    POSITIVE LOGITS
    ees
    0.08
    amework
    0.07
     Rewards
    0.07
    ancer
    0.07
     поврежд
    0.07
    .hr
    0.07
    contrast
    0.07
     Handles
    0.06
     enough
    0.06
    Sql
    0.06
    Activations Density 0.016%

    No Known Activations