© 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. 72432
    Prev
    Next
    INDEX
    Explanations

    coordination

    np_max-act · gemini-2.0-flash

    The neuron reliably lights up on the word “coordination” (and its close variants), flagging mentions of coordinating actions or activities.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    text related to organizational roles and responsibilities in project management.

    oai_token-act-pair · gpt-4o-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
     elephants
    -0.07
     Hernandez
    -0.07
    ('/')
    -0.07
     August
    -0.06
     Burke
    -0.06
     Burning
    -0.06
     magnetic
    -0.06
     bitk
    -0.06
     hamburg
    -0.06
     bre
    -0.06
    POSITIVE LOGITS
     coordination
    0.11
     coordinating
    0.11
     coordinated
    0.10
     coordinator
    0.10
     Coordinator
    0.09
     coordin
    0.09
    Coordinator
    0.09
     cooldown
    0.08
     Coord
    0.08
    coord
    0.08
    Activations Density 0.008%

    No Known Activations