© 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. 43524
    Prev
    Next
    INDEX
    Explanations

    disease

    np_max-act · gemini-2.0-flash

    terms related to cardiac and vascular health conditions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects medical domain terms referring to specific organs, systems, or disease‐related adjectives (e.g., renal, respiratory, ischemic, hypertensive, gastrointestinal).

    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
    _TASK
    -0.07
     Phillips
    -0.07
     جمله
    -0.07
     upbringing
    -0.07
     Kara
    -0.06
    _ACT
    -0.06
     รวม
    -0.06
    _None
    -0.06
     Lottery
    -0.06
    TestMethod
    -0.06
    POSITIVE LOGITS
    _elapsed
    0.07
    fps
    0.06
    //!↵
    0.06
    seek
    0.06
    ess
    0.06
    ẹn
    0.06
    �
    0.06
     thiên
    0.06
    ()},↵
    0.06
    /'+
    0.05
    Activations Density 0.070%

    No Known Activations