© 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. 7313
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron detects formal legal jargon describing a court’s authority or its limits (e.g. phrases about jurisdiction, derogation of law, bounds set by statute).

    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
     adresse
    -0.07
     Capitol
    -0.06
     LiveData
    -0.06
    AxisSize
    -0.06
     better
    -0.06
    -
↵
    -0.06
     speeches
    -0.06
    aj
    -0.06
    sında
    -0.06
    TEXT
    -0.06
    POSITIVE LOGITS
     dán
    0.07
     순
    0.07
     mechanical
    0.07
     tilt
    0.07
    那个
    0.07
     Barcelona
    0.06
    ็ง
    0.06
     Wolfgang
    0.06
    (getString
    0.06
     VOID
    0.06
    Activations Density 0.008%

    No Known Activations