© 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. 30679
    Prev
    Next
    INDEX
    Explanations

    medical surveys

    np_max-act · gemini-2.0-flash

    The neuron responds to terms typical of a study’s methods and results sections—words used in describing survey design, data collection, analysis, and reporting.

    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
    Device
    -0.07
    vní
    -0.06
     durumunda
    -0.06
    toHave
    -0.06
     ICE
    -0.06
    廳
    -0.06
     Authorized
    -0.06
    kovou
    -0.06
    -archive
    -0.06
    专业
    -0.06
    POSITIVE LOGITS
    BOOT
    0.07
     Neh
    0.07
     sluts
    0.06
    }")↵↵
    0.06
    _confirmation
    0.06
    antino
    0.06
     remed
    0.06
     گذ
    0.06
    ='./
    0.06
    oog
    0.06
    Activations Density 0.018%

    No Known Activations