© 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. 13613
    Prev
    Next
    INDEX
    Explanations

    APP

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of the amyloid precursor protein (APP) or related precursor terminology.

    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
    stroke
    -0.07
    Establish
    -0.07
    Slide
    -0.07
     save
    -0.06
     Seconds
    -0.06
     Against
    -0.06
    	id
    -0.06
    �数
    -0.06
     sectors
    -0.06
     Sin
    -0.06
    POSITIVE LOGITS
    CVE
    0.07
     edilmesi
    0.07
    的情况
    0.06
     ΕΛ
    0.06
    mensagem
    0.06
     bilir
    0.06
    奖
    0.06
    Producto
    0.06
     ActivatedRoute
    0.06
    opper
    0.06
    Activations Density 0.001%

    No Known Activations