Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 84814
    Prev
    Next
    INDEX
    Explanations

    background processes

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of running processes or scripts in the background (e.g., “runs in the background,” “run for several days,” “still runs after logout”).

    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
    рогра
    -0.07
    :"-"`↵
    -0.07
     경기
    -0.06
    ı
    -0.06
    또
    -0.06
    !--
    -0.06
    Prod
    -0.06
     SSD
    -0.06
     الطبي
    -0.06
     glossy
    -0.06
    POSITIVE LOGITS
     civilians
    0.06
     ($(
    0.06
     CAS
    0.06
    待
    0.06
     když
    0.06
     лес
    0.06
     Neural
    0.06
     etme
    0.06
     گن
    0.06
    ég
    0.06
    Activations Density 0.054%

    No Known Activations