© 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. 127201
    Prev
    Next
    INDEX
    Explanations

    layer

    np_max-act · gemini-2.0-flash

    The neuron detects references to the specific layers and material components (e.g. organic, light-emitting, transport, emission layers) in OLED device descriptions.

    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
    _Font
    -0.07
     metod
    -0.06
    _for
    -0.06
    _Time
    -0.06
     SHA
    -0.06
     decay
    -0.06
     inquiry
    -0.06
     rozh
    -0.06
    _DOM
    -0.06
     conn
    -0.06
    POSITIVE LOGITS
    heiten
    0.07
    ologna
    0.06
     Laurent
    0.06
    Outside
    0.06
    StateException
    0.06
    тин
    0.06
     unmarried
    0.06
     ΕΛ
    0.06
    ดร
    0.06
    萨
    0.06
    Activations Density 0.013%

    No Known Activations