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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92524
    Prev
    Next
    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash

    This neuron highlights document header and legal-organization tokens—e.g. all‐caps headings, agency or board names, docket numbers, and related formatting elements.

    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
    BU
    -0.08
    378
    -0.07
     APP
    -0.06
    费用
    -0.06
    ريس
    -0.06
    есп
    -0.06
    цу
    -0.06
    346
    -0.06
    Didn
    -0.06
    له
    -0.06
    POSITIVE LOGITS
     dismay
    0.07
    {_
    0.07
     endereco
    0.07
     Angie
    0.06
    .Must
    0.06
     Associate
    0.06
     یکی
    0.06
     Intr
    0.06
    俺
    0.06
     posicion
    0.06
    Activations Density 0.019%

    No Known Activations