© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 125020
    Prev
    Next
    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens in constructions where someone’s eyes or gaze are described as being fixed on something (e.g., “eyes fixated on her…”).

    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
     FPGA
    -0.07
     atte
    -0.07
     Age
    -0.06
    .cl
    -0.06
     seize
    -0.06
     Brent
    -0.06
    례
    -0.06
    TouchListener
    -0.06
    �
    -0.06
    amentos
    -0.06
    POSITIVE LOGITS
     ************************************************
    0.06
     ********************************
    0.06
     inappropriate
    0.06
     Compilation
    0.06
    ื้
    0.06
    殿
    0.06
     consuming
    0.06
    ิเวณ
    0.06
     حرکت
    0.06
     науков
    0.06
    Activations Density 0.014%

    No Known Activations