© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13637
    Prev
    Next
    INDEX
    Explanations

    airlines

    np_max-act · gemini-2.0-flash

    This neuron identifies the names of airlines and budget‐travel brands (e.g., “Southwest,” “Ryan air,” “AirAsia”).

    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
     thiểu
    -0.07
     доступ
    -0.07
    (issue
    -0.06
    	address
    -0.06
    _WIN
    -0.06
     KERNEL
    -0.06
     CIA
    -0.06
    744
    -0.06
    (right
    -0.06
    Contain
    -0.06
    POSITIVE LOGITS
     filmmakers
    0.08
     ↵    ↵
    0.06
     √
    0.06
     Wars
    0.06
     commentator
    0.06
    	and
    0.06
    kbd
    0.06
    urers
    0.06
     Bones
    0.06
     Rebel
    0.06
    Activations Density 0.026%

    No Known Activations