Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 84665
    Prev
    Next
    INDEX
    Explanations

    minority business enterprises

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of small or minority-owned business classifications (e.g., “small business,” “minority-owned”).

    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
    ॉक
    -0.07
    armacy
    -0.06
    وه
    -0.06
     paycheck
    -0.06
    ILT
    -0.06
     витами
    -0.06
    ्कर
    -0.06
    -be
    -0.06
    яв
    -0.06
    anela
    -0.06
    POSITIVE LOGITS
     healer
    0.08
    (numbers
    0.07
     Farmers
    0.07
     Fu
    0.07
     Continuing
    0.06
     foreign
    0.06
    regulated
    0.06
     Miss
    0.06
    ![
    0.06
    	Use
    0.06
    Activations Density 0.006%

    No Known Activations