© 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. 91432
    Prev
    Next
    INDEX
    Explanations

    arbitration agreement

    np_max-act · gemini-2.0-flash

    The neuron activates on terms and phrases referring to arbitration (e.g. “arbitration,” “arbitrator,” “arbitrate,” “arbitration agreement”), effectively detecting mentions of arbitration clauses or proceedings.

    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
    (rank
    -0.08
     assistant
    -0.07
     statute
    -0.06
    bruary
    -0.06
     drones
    -0.06
     contrary
    -0.06
     peuvent
    -0.06
    asures
    -0.06
    '_
    -0.06
    avior
    -0.06
    POSITIVE LOGITS
    SY
    0.06
    .setError
    0.06
    _CL
    0.06
    раб
    0.06
     initialise
    0.06
     scripted
    0.06
    RECT
    0.06
    اگ
    0.06
    خل
    0.06
    QQ
    0.06
    Activations Density 0.003%

    No Known Activations