© 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. 91424
    Prev
    Next
    INDEX
    Explanations

    Web development frameworks

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of software technologies or development platforms (frameworks, languages, and cloud services).

    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
     overwhel
    -0.06
     Billion
    -0.06
    桌
    -0.06
     churches
    -0.06
    合同
    -0.06
     username
    -0.06
    (dataSource
    -0.06
     dnes
    -0.06
     withstand
    -0.06
    ^^^^
    -0.06
    POSITIVE LOGITS
    soever
    0.07
    registro
    0.06
    ++;
    ↵
    0.06
    LOUD
    0.06
    (Html
    0.06
    sez
    0.06
    プラ
    0.06
     жар
    0.06
     Mutable
    0.06
     trai
    0.06
    Activations Density 0.059%

    No Known Activations