© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 103618
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron fires on passages describing transfers of ownership or title—sentences about buildings being sold, gifted, or purchased, along with the parties and dates involved.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    information about historical buildings or architectural structures.

    oai_token-act-pair · gpt-4o-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
     również
    -0.07
    桥
    -0.06
    وات
    -0.06
    opoly
    -0.06
    volt
    -0.06
    revolution
    -0.06
    .bundle
    -0.06
    .offsetHeight
    -0.06
     पद
    -0.06
    >(),↵
    -0.05
    POSITIVE LOGITS
     fictional
    0.07
     Tatto
    0.07
     assortment
    0.07
     substant
    0.07
     Scottish
    0.06
    .setTime
    0.06
     Delaware
    0.06
     Farmers
    0.06
     elabor
    0.06
     nutrients
    0.06
    Activations Density 0.012%

    No Known Activations