© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89044
    Prev
    Next
    INDEX
    Explanations

    tribe

    np_max-act · gemini-2.0-flash

    This neuron activates whenever the text mentions “tribe” (including its plural form “tribes”).

    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
     aeros
    -0.07
    Cancelled
    -0.07
     Evelyn
    -0.07
     cosmetics
    -0.07
     홈페이지
    -0.06
    egers
    -0.06
     magazines
    -0.06
     розрах
    -0.06
    форт
    -0.06
     Lens
    -0.06
    POSITIVE LOGITS
     tribal
    0.13
     tribe
    0.12
     tribes
    0.12
     Tribe
    0.11
     Tribal
    0.10
     Trib
    0.10
     Tribunal
    0.10
     trib
    0.09
     tribunal
    0.09
     ib
    0.08
    Activations Density 0.004%

    No Known Activations