© 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. 8909
    Prev
    Next
    INDEX
    Explanations

    ”,

    np_max-act · gemini-2.0-flash

    The neuron is primarily triggered by mentions of configuration-style code—especially environment‐variable references and config settings in Rails initializer files.

    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
    (train
    -0.06
    存
    -0.06
    )
↵
    -0.06
     umbrella
    -0.06
    	case
    -0.06
     abund
    -0.06
    devices
    -0.06
    _layer
    -0.06
     Constants
    -0.06
    Flight
    -0.06
    POSITIVE LOGITS
    рати
    0.07
    яви
    0.07
     prostituer
    0.07
    raç
    0.07
    InnerHTML
    0.06
     Automotive
    0.06
     svou
    0.06
     dwind
    0.06
    rest
    0.06
    CLA
    0.06
    Activations Density 0.155%

    No Known Activations