© 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. 56017
    Prev
    Next
    INDEX
    Explanations

    .Lock

    np_max-act · gemini-2.0-flash

    This neuron activates on mutex (and similar) synchronization calls—i.e. `.Lock`, `.Unlock`, and related lock/unlock method invocations.

    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
    �
    -0.06
    ndef
    -0.06
     unspecified
    -0.06
     leží
    -0.06
    !_
    -0.06
     البي
    -0.06
     =================================================
    -0.06
     =================================
    -0.06
    	gr
    -0.06
     southern
    -0.06
    POSITIVE LOGITS
     बन
    0.07
     Fellowship
    0.06
     isc
    0.06
     모집
    0.06
     HI
    0.06
    시간
    0.06
     Madden
    0.06
     Fasc
    0.06
    �断
    0.06
     worked
    0.06
    Activations Density 0.002%

    No Known Activations