© 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. 85779
    Prev
    Next
    INDEX
    Explanations

    the/a

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of sports contexts—particularly descriptions of athletes, events, or athletic performance.

    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
     QAction
    -0.06
     RegExp
    -0.06
    upgrade
    -0.06
    -Men
    -0.06
     negotiating
    -0.06
    MT
    -0.06
    LOOR
    -0.06
    	process
    -0.06
     จำ
    -0.06
    Upgrade
    -0.06
    POSITIVE LOGITS
     massa
    0.07
    惠
    0.06
     všichni
    0.06
    致
    0.06
     geçerli
    0.06
    =\"%
    0.06
     Rookie
    0.06
    ฉ
    0.06
    izioni
    0.06
    Tit
    0.06
    Activations Density 0.026%

    No Known Activations