Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 13356
    Prev
    Next
    INDEX
    Explanations

    surgical complications

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of “incisional” (e.g., inc-ision-al) hernias or related surgical‐incision hernia terms.

    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
     condiciones
    -0.07
    tryside
    -0.07
    금
    -0.06
     potent
    -0.06
     CPPUNIT
    -0.06
    ipheral
    -0.06
    znám
    -0.06
    Practice
    -0.06
    -Time
    -0.06
     않은
    -0.06
    POSITIVE LOGITS
     Structures
    0.08
    速度
    0.07
    IGHL
    0.07
     Friendship
    0.07
    -image
    0.06
     minds
    0.06
    URI
    0.06
     �
    0.06
    اورپ
    0.06
    کنان
    0.06
    Activations Density 0.012%

    No Known Activations