© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59445
    Prev
    Next
    INDEX
    Explanations

    United States, ability

    np_max-act · gemini-2.0-flash

    The neuron flags mentions of formal U.S. legal statutes, government titles, and named acts (e.g. “Civil Rights Act,” “Title IX,” agency and program names).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    หม
    -0.07
    еч
    -0.06
    _CS
    -0.06
    086
    -0.06
    .DateTimePicker
    -0.06
    宗
    -0.06
    幅
    -0.06
    145
    -0.06
     Constr
    -0.06
     valves
    -0.06
    POSITIVE LOGITS
    حق
    0.07
    ment
    0.07
    vir
    0.06
    уча
    0.06
    imations
    0.06
    >()->
    0.06
    claimer
    0.06
    _SCHED
    0.06
    .cy
    0.06
    /movie
    0.06
    Activations Density 0.103%

    No Known Activations