© 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. 68571
    Prev
    Next
    INDEX
    Explanations

    Title VII employment discrimination

    np_max-act · gemini-2.0-flash

    This neuron detects citations of U.S. federal statutes—especially Title VII (Civil Rights Act of 1964) and related laws (e.g. ADEA)—including their section numbers and enactment dates.

    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
     $$
    -0.06
     впол
    -0.06
    ENDOR
    -0.06
     Karma
    -0.06
     Sele
    -0.06
    -urlencoded
    -0.06
     znam
    -0.06
    Discover
    -0.06
     actively
    -0.06
    affected
    -0.06
    POSITIVE LOGITS
     wrestling
    0.07
    uplicates
    0.07
    _MUTEX
    0.06
     liters
    0.06
    notations
    0.06
    рош
    0.06
    reu
    0.06
    ?q
    0.06
    chrift
    0.06
     berg
    0.06
    Activations Density 0.002%

    No Known Activations