© 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. 44945
    Prev
    Next
    INDEX
    Explanations

    program

    np_max-act · gemini-2.0-flash

    The neuron detects the formal patent–style descriptions of a plant as “a product of a planned breeding program” (and related boilerplate about the invention’s origin, objective, and parentage).

    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
    recent
    -0.06
    Construct
    -0.06
     jealous
    -0.06
    ritable
    -0.06
    .Owner
    -0.06
    (work
    -0.06
    anghai
    -0.06
    -Co
    -0.06
    	with
    -0.06
    Operators
    -0.06
    POSITIVE LOGITS
    252
    0.07
    ntp
    0.07
     р
    0.07
     हज
    0.07
     土
    0.06
    onto
    0.06
    eci
    0.06
    ตะว
    0.06
    dataProvider
    0.06
     мік
    0.06
    Activations Density 0.004%

    No Known Activations