© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 65218
    Prev
    Next
    INDEX
    Explanations

    service

    np_max-act · gemini-2.0-flash

    technical terms and jargon related to web services and programming frameworks.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects mentions of web‐service–related terms (e.g. “web service,” “WebService,” WSDL/SOAP/WCF, 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
     pointed
    -0.06
     page
    -0.06
    周
    -0.06
     granularity
    -0.06
     �
    -0.06
     Antique
    -0.06
    parseInt
    -0.06
     telescope
    -0.06
    773
    -0.06
     enthusiast
    -0.06
    POSITIVE LOGITS
    scribed
    0.07
    WebService
    0.07
    Ws
    0.07
     trainer
    0.07
     Erik
    0.07
    _using
    0.07
    /services
    0.07
    /libs
    0.06
    ักษ
    0.06
    _prior
    0.06
    Activations Density 0.003%

    No Known Activations