© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 128501
    Prev
    Next
    INDEX
    Explanations

    legal/formal language

    np_max-act · gemini-2.0-flash

    This neuron detects references to legal code sections and numeric citations (e.g., section numbers, part identifiers) in the text.

    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
    ดย
    -0.06
    Teachers
    -0.06
     advisers
    -0.06
     Над
    -0.06
    .hero
    -0.06
    庭
    -0.06
    eners
    -0.06
    算
    -0.06
    osals
    -0.06
    subtotal
    -0.06
    POSITIVE LOGITS
    .QRect
    0.07
     CG
    0.07
     contar
    0.07
    consulta
    0.07
     qx
    0.06
     lez
    0.06
     ForeignKey
    0.06
    userInfo
    0.06
     demonstr
    0.06
    $',
    0.06
    Activations Density 0.004%

    No Known Activations