© 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. 56304
    Prev
    Next
    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash

    This neuron detects formal references to legal disciplinary proceedings against lawyers (e.g. headings like “In re Complaint,” “Accused,” “Disciplinary,” “Bar,” and related case‐style metadata).

    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
     Sat
    -0.08
     Mode
    -0.08
     RD
    -0.07
     Av
    -0.07
     mode
    -0.07
    .rep
    -0.07
     با
    -0.07
     WWW
    -0.07
    Mount
    -0.07
     meds
    -0.06
    POSITIVE LOGITS
    -таки
    0.07
    (serializers
    0.06
    _lib
    0.06
    iedades
    0.06
    overflow
    0.06
    []
    0.06
    .entrySet
    0.06
    홈
    0.06
    hope
    0.06
     благ
    0.06
    Activations Density 0.011%

    No Known Activations