© 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. 91377
    Prev
    Next
    INDEX
    Explanations

    developer

    np_max-act · gemini-2.0-flash

    discussions related to programming and technical questions about software development.

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

    This neuron detects mentions of programming- or development-related job titles (e.g. “programmer,” “developer,” “evangelist”).

    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
    .button
    -0.07
     MessageBox
    -0.06
    419
    -0.06
    Tables
    -0.06
     mounts
    -0.06
    globals
    -0.06
    _program
    -0.05
     arena
    -0.05
     Es
    -0.05
     університ
    -0.05
    POSITIVE LOGITS
    -income
    0.07
    γωγ
    0.07
     assigning
    0.07
    ugging
    0.06
    ського
    0.06
    ço
    0.06
     червня
    0.06
     income
    0.06
    скому
    0.06
     Основ
    0.06
    Activations Density 0.017%

    No Known Activations