© 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. 124754
    Prev
    Next
    INDEX
    Explanations

    global context

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of global reach or worldwide presence (e.g. “around the world,” “worldwide”).

    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
    Reserved
    -0.06
    503
    -0.06
     Refugee
    -0.06
    /job
    -0.06
     truths
    -0.06
    Europe
    -0.06
    461
    -0.06
    ysize
    -0.05
    _empty
    -0.05
     Ph
    -0.05
    POSITIVE LOGITS
    ряд
    0.08
    스터
    0.08
    anoi
    0.07
    �
    0.07
     shutting
    0.07
    微笑
    0.07
    言
    0.07
    .getClass
    0.06
     putt
    0.06
    .setStatus
    0.06
    Activations Density 0.020%

    No Known Activations