© 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. 13386
    Prev
    Next
    INDEX
    Explanations

    artificial intelligence and algorithms

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of AI technology—particularly references to AI systems, models, and their behavior in decision-making.

    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
     FAMILY
    -0.07
    ð
    -0.06
     ObjectMapper
    -0.06
     WV
    -0.06
    DIR
    -0.06
     FO
    -0.06
    ван
    -0.06
    odzi
    -0.06
     将
    -0.06
    asso
    -0.06
    POSITIVE LOGITS
    .serialization
    0.07
     getColor
    0.06
     rel
    0.06
     út
    0.06
    [layer
    0.06
     glEnable
    0.06
    %</
    0.06
     सभ
    0.06
     Dataset
    0.06
     مركز
    0.06
    Activations Density 0.013%

    No Known Activations