© 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. 42735
    Prev
    Next
    INDEX
    Explanations

    BufferedReader

    np_max-act · gemini-2.0-flash

    The neuron activates on instantiations of Java BufferedReader (i.e., when a BufferedReader is created to read input streams).

    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
     Pound
    -0.07
     rods
    -0.06
      
    -0.06
    時に
    -0.06
    -pay
    -0.06
     pang
    -0.06
    getSingleton
    -0.06
    DAY
    -0.06
     Page
    -0.06
     coordinator
    -0.06
    POSITIVE LOGITS
     BufferedReader
    0.11
    	BufferedReader
    0.09
    itude
    0.07
    edReader
    0.07
    Presence
    0.06
    建筑
    0.06
    ThemeProvider
    0.06
    }↵↵↵
    0.06
    РА
    0.06
     возв
    0.06
    Activations Density 0.000%

    No Known Activations