© 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. 7881
    Prev
    Next
    INDEX
    Explanations

    service

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of network service quality and Quality-of-Service (QoS) concepts.

    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
    Conclusion
    -0.07
    Л
    -0.07
    ł
    -0.07
     boyut
    -0.07
    alamat
    -0.07
     htonl
    -0.07
    uthor
    -0.06
     captive
    -0.06
    .pivot
    -0.06
     implants
    -0.06
    POSITIVE LOGITS
     Wass
    0.07
    .Edit
    0.07
     FS
    0.07
    ственного
    0.07
     Hum
    0.07
    âb
    0.06
     ApplicationController
    0.06
     Dien
    0.06
     Gest
    0.06
    _ENCODING
    0.06
    Activations Density 0.006%

    No Known Activations