© 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. 772
    Prev
    Next
    INDEX
    Explanations

    services

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect ASP .NET Core authentication setup code—e.g. calls to AddAuthentication/UseAuthentication, ConfigureServices/Configure methods, OpenIdConnect or JwtBearer configuration, and related middleware tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    concepts related to application configuration and dependency injection in .NET Core.

    oai_token-act-pair · gpt-4o-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
     vay
    -0.06
     mới
    -0.06
    채
    -0.06
    emails
    -0.06
     lado
    -0.06
     구글상위
    -0.06
     contador
    -0.06
     lebih
    -0.06
    提示
    -0.05
     envisioned
    -0.05
    POSITIVE LOGITS
     organising
    0.06
    <QString
    0.06
    بول
    0.06
    يط
    0.06
     assay
    0.06
    ingle
    0.06
     Nottingham
    0.06
     ор
    0.06
     substr
    0.06
     απο
    0.06
    Activations Density 0.005%

    No Known Activations