© 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. 74684
    Prev
    Next
    INDEX
    Explanations

    Code, software development

    np_max-act · gemini-2.0-flash

    This neuron fires on simple field‐assignment statements (especially `this.field = parameter;`) in constructors and similar initializer code.

    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
     vocational
    -0.07
    urities
    -0.07
     Owen
    -0.06
     needy
    -0.06
     squeeze
    -0.06
    Extreme
    -0.06
    THOOK
    -0.06
     specialty
    -0.06
     renov
    -0.06
    гал
    -0.06
    POSITIVE LOGITS
     tông
    0.06
    DIG
    0.06
     <
    0.06
    �
    0.06
     percentage
    0.06
     Prism
    0.06
    атков
    0.06
     blatant
    0.06
    ิ
    0.06
    <Long
    0.06
    Activations Density 0.004%

    No Known Activations