© 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. 29510
    Prev
    Next
    INDEX
    Explanations

    binding

    np_max-act · gemini-2.0-flash

    This neuron detects French legal wording that marks something as binding or obligatory (e.g. parts of “contraignante pour”).

    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
    Cisco
    -0.09
    unifu
    -0.06
    روم
    -0.06
     Cisco
    -0.06
     Ecuador
    -0.06
    试
    -0.06
     bowed
    -0.06
     tx
    -0.06
    	dc
    -0.06
     Hoff
    -0.06
    POSITIVE LOGITS
     作
    0.07
     binding
    0.06
    _engine
    0.06
     оп
    0.06
    istinguish
    0.06
     Capitals
    0.06
    -party
    0.06
    ประช
    0.06
     Santana
    0.06
    .Hidden
    0.06
    Activations Density 0.010%

    No Known Activations