© 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
    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. 761
    Prev
    Next
    INDEX
    Explanations

    Circuit

    np_max-act · gemini-2.0-flash

    This neuron detects references to U.S. federal appellate courts by name and circuit (e.g., “UNITED STATES COURT OF APPEALS Sixth Circuit”).

    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
    韓
    -0.07
     mostra
    -0.07
    .tel
    -0.06
    олуч
    -0.06
     Ông
    -0.06
    .CharField
    -0.06
     ]);
    -0.06
    ジョ
    -0.06
     Premiere
    -0.06
    '>{
    -0.06
    POSITIVE LOGITS
    TAB
    0.07
     discounted
    0.07
     evolve
    0.07
    nts
    0.07
    arian
    0.06
    ẩy
    0.06
    ibration
    0.06
     Loaded
    0.06
     customize
    0.06
    module
    0.06
    Activations Density 0.002%

    No Known Activations