© 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. 43329
    Prev
    Next
    INDEX
    Explanations

    attr

    np_max-act · gemini-2.0-flash

    This neuron detects code dealing with pthread mutex attribute objects (e.g. uses of “attr” in pthread_mutexattr_init, settype, destroy, etc.).

    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
    ocoder
    -0.06
     WR
    -0.06
    飾
    -0.06
     booking
    -0.06
    قی
    -0.06
     \↵
    -0.06
     mathematics
    -0.06
     addr
    -0.06
     reaches
    -0.05
     werde
    -0.05
    POSITIVE LOGITS
    omers
    0.07
    mensagem
    0.07
    terr
    0.06
     ConcurrentHashMap
    0.06
    ankan
    0.06
    /************************************************************************
    0.06
    orgh
    0.06
     Dependencies
    0.06
    етод
    0.06
    โลย
    0.06
    Activations Density 0.002%

    No Known Activations