© 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. 43022
    Prev
    Next
    INDEX
    Explanations

    optical

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of electronic and photonic materials or devices—terms like “organic electronics,” “photovoltaics,” “photonics,” “LED,” and “semiconductor lasers.”

    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
     cups
    -0.07
    boom
    -0.07
     investigación
    -0.06
     Hearts
    -0.06
     Kristen
    -0.06
    анд
    -0.06
     право
    -0.06
    izar
    -0.06
    "`↵
    -0.06
    χαν
    -0.06
    POSITIVE LOGITS
     Annex
    0.06
     dusk
    0.06
    _linux
    0.06
     kıl
    0.06
     Offers
    0.06
    ROAD
    0.06
     stationed
    0.06
    _look
    0.06
     державної
    0.06
     mention
    0.06
    Activations Density 0.108%

    No Known Activations