© 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. 30104
    Prev
    Next
    INDEX
    Explanations

    money and goods

    np_max-act · gemini-2.0-flash

    phrases related to online purchases and transactions.

    oai_token-act-pair · gpt-4oTriggered by @tcai

    The neuron detects words about financial exchanges—i.e. terms for moving value (transactions, payments, transfers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    descriptions and characteristics of cryptocurrencies, particularly focusing on their functions and underlying technologies.

    oai_token-act-pair · gpt-4o-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
    Firestore
    -0.07
    iron
    -0.07
    Scripts
    -0.06
    โปร
    -0.06
    _bo
    -0.06
     Numbers
    -0.06
     ธ
    -0.06
     starting
    -0.06
     loan
    -0.06
    .FloatTensor
    -0.06
    POSITIVE LOGITS
    lice
    0.07
     cung
    0.07
    Uploader
    0.06
    arine
    0.06
     jaws
    0.06
     weary
    0.06
     putas
    0.06
     upright
    0.06
    porte
    0.06
    illet
    0.06
    Activations Density 0.017%

    No Known Activations