© 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. 92107
    Prev
    Next
    INDEX
    Explanations

    weight

    np_max-act · gemini-2.0-flash

    The neuron activates on biomedical terms specifically related to obesity and its surgical treatment (bariatric surgery) and associated weight‐loss outcomes.

    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
     Сам
    -0.07
     infections
    -0.07
     Home
    -0.06
     dementia
    -0.06
    adas
    -0.06
    azole
    -0.06
    oked
    -0.06
    istr
    -0.06
    _steps
    -0.06
    .quick
    -0.06
    POSITIVE LOGITS
    처
    0.07
     أد
    0.06
    ขว
    0.06
    ولة
    0.06
     prvním
    0.06
     เมตร
    0.06
    .var
    0.06
     suche
    0.06
     cris
    0.06
    Marsh
    0.06
    Activations Density 0.006%

    No Known Activations