© 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
    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. 88968
    Prev
    Next
    INDEX
    Explanations

    your

    np_max-act · gemini-2.0-flash

    The neuron flags terms that directly address the reader or their organization—particularly second‐person words like “you” and “your” and related audience/business nouns (e.g. “company,” “group,” “employees,” “delegates”).

    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
    Very
    -0.07
     demolition
    -0.06
    QObject
    -0.06
    :&
    -0.06
    Crypt
    -0.06
    Super
    -0.06
    Destination
    -0.06
    endir
    -0.06
    _ICON
    -0.06
    $args
    -0.06
    POSITIVE LOGITS
    ابر
    0.07
    liği
    0.06
     주요
    0.06
     TECH
    0.06
    ιβ
    0.06
     PROPERTY
    0.06
     캐
    0.06
    )
    
    ↵
    0.06
     rendez
    0.06
     травня
    0.06
    Activations Density 0.053%

    No Known Activations