© 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. 54010
    Prev
    Next
    INDEX
    Explanations

    they

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on names of sports teams (especially college/pro football team names).

    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
    469
    -0.07
    428
    -0.07
     war
    -0.06
     nurse
    -0.06
    el
    -0.06
     War
    -0.06
    efa
    -0.06
     nurses
    -0.06
     exemptions
    -0.06
     البد
    -0.06
    POSITIVE LOGITS
    گانی
    0.08
    .scrollView
    0.07
     campaigning
    0.07
    鮮
    0.06
    ―
    0.06
    jspb
    0.06
    �
    0.06
     심
    0.06
    _B
    0.06
     FactoryBot
    0.06
    Activations Density 0.020%

    No Known Activations