© 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. 73902
    Prev
    Next
    INDEX
    Explanations

    legal court

    np_max-act · gemini-2.0-flash

    legal terminology and concepts related to lawsuits and claims for damages.

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

    This neuron detects references to court rulings or judicial outcomes (e.g., words like “rendered,” “judgment,” “decision,” and similar terms describing legal decisions).

    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
    ヴ
    -0.07
    -Javadoc
    -0.07
    ,…↵↵
    -0.07
     Nhưng
    -0.06
     Binding
    -0.06
     neigh
    -0.06
     зберіг
    -0.06
    _im
    -0.06
    があった
    -0.06
     Sunday
    -0.06
    POSITIVE LOGITS
    _e
    0.06
     retract
    0.06
    487
    0.06
     زیب
    0.06
    _invalid
    0.06
    .click
    0.06
     deferred
    0.06
    .partial
    0.06
    (firstName
    0.06
     sod
    0.06
    Activations Density 0.021%

    No Known Activations