© 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. 43286
    Prev
    Next
    INDEX
    Explanations

    car

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of vehicles or automotive contexts (e.g., car, Jeep, vehicle, model year).

    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
     Barnes
    -0.07
    Newsletter
    -0.06
    Composer
    -0.06
     newSize
    -0.06
     Astronomy
    -0.06
     Nachricht
    -0.06
    Aside
    -0.06
    ジェ
    -0.06
    ότε
    -0.06
    	temp
    -0.06
    POSITIVE LOGITS
     الاس
    0.07
     champ
    0.06
     gazet
    0.06
    esthetic
    0.06
    日本
    0.06
     under
    0.06
     نت
    0.06
    +xml
    0.05
    สมบ
    0.05
     Верхов
    0.05
    Activations Density 0.032%

    No Known Activations