© 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. 110743
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    legal case citations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects boilerplate statements about a court opinion’s publication status—specifically phrases like “certified for publication or ordered published.”

    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
    查询
    -0.07
     تازه
    -0.06
     ui
    -0.06
    .elem
    -0.06
     افز
    -0.06
    _UN
    -0.06
     Appliances
    -0.06
    _after
    -0.06
    丁目
    -0.06
    这种
    -0.06
    POSITIVE LOGITS
    (Application
    0.07
     đài
    0.06
    ưng
    0.06
     defy
    0.06
    works
    0.06
     derp
    0.06
     compliments
    0.06
    ент
    0.06
    ews
    0.06
    ue
    0.06
    Activations Density 0.000%

    No Known Activations