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. 90103
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron fires on CamelCase or PascalCase code identifiers (e.g. class and method names) in the MVC/C# snippets.

    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
     свого
    -0.07
     شهر
    -0.06
    [table
    -0.06
     ################################################################
    -0.06
    ,sizeof
    -0.06
    sys
    -0.06
     '\\'
    -0.06
    _definitions
    -0.06
    �
    -0.06
     startled
    -0.06
    POSITIVE LOGITS
    чества
    0.07
     Cousins
    0.07
    oli
    0.06
    .GridColumn
    0.06
    (figsize
    0.06
     massa
    0.06
    OLS
    0.06
     Brazil
    0.06
    .G
    0.06
     lavoro
    0.06
    Activations Density 0.037%

    No Known Activations