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. 1098
    Prev
    Next
    INDEX
    Explanations

    us

    np_max-act · gemini-2.0-flash

    This neuron fires on inclusive, first-person plural phrasing—instances of “we,” “us,” or related calls to collective action or sharing.

    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
    초
    -0.06
     coupe
    -0.06
    currency
    -0.06
     Tmax
    -0.06
    พบ
    -0.06
     bedroom
    -0.06
    .concatenate
    -0.06
    Assets
    -0.06
    _hot
    -0.05
    PEndPoint
    -0.05
    POSITIVE LOGITS
     нас
    0.07
     Readonly
    0.07
       	
    0.07
    _XML
    0.06
    摘
    0.06
    (bc
    0.06
    BigDecimal
    0.06
     mü
    0.06
     HASH
    0.06
    .pixel
    0.06
    Activations Density 0.035%

    No Known Activations