© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 74161
    Prev
    Next
    INDEX
    Explanations

    product descriptions and requests

    np_max-act · gemini-2.0-flash

    payment and shipping-related terms in e-commerce contexts.

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

    The neuron detects words and phrases in the seller’s terms and conditions section—especially around payment, shipping, returns, and policy details.

    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
    anonymous
    -0.07
    Bluetooth
    -0.06
    xEF
    -0.06
     záznam
    -0.06
    OWNER
    -0.06
     asyncio
    -0.06
    ikel
    -0.06
     近
    -0.06
    ifact
    -0.06
    社会
    -0.06
    POSITIVE LOGITS
     fellow
    0.06
     поє
    0.06
    스티
    0.06
    กราคม
    0.06
     ↓
    0.06
     दक
    0.06
    enegro
    0.06
     enjoy
    0.06
     chave
    0.06
     замен
    0.06
    Activations Density 0.026%

    No Known Activations