© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13374
    Prev
    Next
    INDEX
    Explanations

    -life

    np_max-act · gemini-2.0-flash

    The neuron is keyed to references to work-life balance challenges—particularly terms around burnout and mental-health strain.

    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
     Mara
    -0.07
     Ανα
    -0.07
     Assessment
    -0.06
     programming
    -0.06
     göre
    -0.06
    ubat
    -0.06
    olesale
    -0.06
     خر
    -0.06
     대
    -0.06
     Vert
    -0.06
    POSITIVE LOGITS
    nez
    0.07
    取得
    0.07
    ivy
    0.07
     jíd
    0.07
     pháp
    0.07
    )];
↵
    0.06
     segmented
    0.06
    avě
    0.06
    MainWindow
    0.06
    @Setter
    0.06
    Activations Density 0.008%

    No Known Activations