Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 85459
    Prev
    Next
    INDEX
    Explanations

    .NET

    np_max-act · gemini-2.0-flash

    This neuron activates on references to the ASP .NET framework (mentions of “ASP.NET” or “asp.net”).

    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
     refuse
    -0.07
     immoral
    -0.06
     African
    -0.06
     respondents
    -0.06
     فروش
    -0.06
     delights
    -0.06
     Sister
    -0.06
     advises
    -0.06
     followers
    -0.06
    _ass
    -0.06
    POSITIVE LOGITS
    无码
    0.07
    .NET
    0.07
    kening
    0.07
    ,並
    0.07
     Git
    0.07
     stark
    0.06
     полож
    0.06
    subset
    0.06
    零
    0.06
    NSData
    0.06
    Activations Density 0.002%

    No Known Activations