© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12541
    Prev
    Next
    INDEX
    Explanations

    self-care

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on self-referential and second-person advice terms—especially words like “you,” “your,” “self,” and “self-care.”

    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
    tah
    -0.07
    anc
    -0.07
     Coch
    -0.06
     план
    -0.06
    浜
    -0.06
     tant
    -0.06
    coupon
    -0.06
    äter
    -0.06
     هذه
    -0.06
    _.
    -0.06
    POSITIVE LOGITS
     skyline
    0.06
     Venture
    0.06
     колич
    0.06
     Brave
    0.06
    toDouble
    0.06
     hides
    0.06
     Primary
    0.06
    (KeyCode
    0.06
     Kai
    0.06
    .isSelected
    0.06
    Activations Density 0.033%

    No Known Activations