© 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. 6313
    Prev
    Next
    INDEX
    Explanations

    solidity

    np_max-act · gemini-2.0-flash

    smart contracts that implement the MasterChef pattern for decentralized finance applications.

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

    The neuron is triggered by references to the Solidity programming language (e.g. “pragma solidity” and OpenZeppelin imports).

    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
    -CS
    -0.06
    만원
    -0.06
     �
    -0.06
    -Free
    -0.06
    LayoutParams
    -0.06
     waivers
    -0.06
     zpracování
    -0.06
    Titulo
    -0.06
     बदल
    -0.06
    Formatting
    -0.06
    POSITIVE LOGITS
    (xml
    0.07
     Cuba
    0.07
    сед
    0.07
    yyval
    0.07
    _land
    0.07
     جستارهای
    0.07
     solidity
    0.07
    mitt
    0.06
    Greek
    0.06
     důvod
    0.06
    Activations Density 0.001%

    No Known Activations