© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 73922
    Prev
    Next
    INDEX
    Explanations

    .Linq

    np_max-act · gemini-2.0-flash

    code snippets related to programming errors and debugging.

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

    The neuron fires on C# import lines for the LINQ namespace, i.e. “using System.Linq.”

    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
    child
    -0.07
    _packets
    -0.06
     Only
    -0.06
    _filtered
    -0.06
     Liability
    -0.06
    TOCOL
    -0.06
    ï
    -0.06
    _VALUES
    -0.06
     Parses
    -0.06
    gom
    -0.06
    POSITIVE LOGITS
     шт
    0.06
     unders
    0.06
     smě
    0.06
    .pt
    0.06
     νεφ
    0.06
    (inputs
    0.06
    MethodImpl
    0.06
    .RequestParam
    0.06
     маст
    0.06
     paramet
    0.06
    Activations Density 0.001%

    No Known Activations