© 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. 43251
    Prev
    Next
    INDEX
    Explanations

    district

    np_max-act · gemini-2.0-flash

    The neuron is keyed to occurrences of the word “district,” as used in court or jurisdiction headings.

    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
    period
    -0.07
    Gün
    -0.07
    れた
    -0.07
     утеп
    -0.06
    Aura
    -0.06
     periods
    -0.06
     коштів
    -0.06
    ์อ
    -0.06
     consult
    -0.06
     уклад
    -0.06
    POSITIVE LOGITS
    ByExample
    0.06
     빈
    0.06
    …)↵↵
    0.06
     )}↵
    0.06
     воздейств
    0.06
     catcher
    0.06
     vzdál
    0.06
     Uncategorized
    0.06
    ْس
    0.06
     Ottawa
    0.06
    Activations Density 0.004%

    No Known Activations