© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 38099
    Prev
    Next
    INDEX
    Explanations

    numbered legal conditions

    np_max-act · gemini-2.0-flash

    references to legal cases involving criminal proceedings.

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

    This neuron detects the numbered sub-elements of legal or statutory tests (e.g. the “(1) … (2) … (3)” markers used to list the required elements of a prima facie case).

    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
    Moved
    -0.06
     ){↵
    -0.06
    NSInteger
    -0.06
    crawler
    -0.06
     тим
    -0.06
     Hurricane
    -0.06
     funciones
    -0.06
     indicate
    -0.06
     pokud
    -0.06
    EObject
    -0.06
    POSITIVE LOGITS
    挥
    0.06
     جو
    0.06
     оборуд
    0.06
     contentious
    0.06
    ΩΣ
    0.06
    교회
    0.06
    َج
    0.06
    όρ
    0.06
     través
    0.06
     discriminator
    0.06
    Activations Density 0.004%

    No Known Activations