© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30844
    Prev
    Next
    INDEX
    Explanations

    deaths

    np_max-act · gemini-2.0-flash

    This neuron detects the major section headings (like “Events,” “Births,” “Deaths”) in a year-summary document.

    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
     lookup
    -0.06
    CPP
    -0.06
     آباد
    -0.06
     갤로그
    -0.06
     purity
    -0.06
    غن
    -0.06
     sanitized
    -0.06
     directory
    -0.06
    libraries
    -0.06
    ök
    -0.06
    POSITIVE LOGITS
     quận
    0.07
     Dani
    0.06
    	df
    0.06
     systemFontOfSize
    0.06
    	div
    0.06
    ++)
    0.06
     }↵↵↵
    0.06
     cow
    0.06
    ி�
    0.06
    __)
    0.06
    Activations Density 0.002%

    No Known Activations