Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43725
    Prev
    Next
    INDEX
    Explanations

    clerk

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of the court clerk—especially directives of the form “Clerk … to …” in judicial orders.

    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
     مح
    -0.07
    네요
    -0.06
    umpt
    -0.06
     نیرو
    -0.06
     제출
    -0.06
    导
    -0.06
    導
    -0.06
     vene
    -0.06
    .Record
    -0.06
    われた
    -0.06
    POSITIVE LOGITS
    (route
    0.07
    يان
    0.07
    [@"
    0.06
     ENTRY
    0.06
     NSW
    0.06
    =length
    0.06
    �
    0.06
    ?,?,
    0.06
    @"↵
    0.06
    ΕΧ
    0.06
    Activations Density 0.004%

    No Known Activations