© 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. 9142
    Prev
    Next
    INDEX
    Explanations

    job titles

    np_max-act · gemini-2.0-flash

    This neuron identifies words denoting formal roles or job titles (e.g., “president,” “manager,” “CFO,” “employee,” etc.).

    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
     concession
    -0.06
    utral
    -0.06
    港
    -0.06
    oubted
    -0.06
    ngthen
    -0.06
     Formal
    -0.06
    屬
    -0.06
     Libraries
    -0.06
     Dynamic
    -0.06
    NSUInteger
    -0.06
    POSITIVE LOGITS
    .getTransaction
    0.07
    RET
    0.07
    ARIO
    0.07
    [table
    0.06
     Buddh
    0.06
     phút
    0.06
    луж
    0.06
     carro
    0.06
    ário
    0.06
    	entity
    0.06
    Activations Density 0.062%

    No Known Activations