© 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
    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. 110428
    Prev
    Next
    INDEX
    Explanations

    Common suffixes

    np_max-act · gemini-2.0-flash

    This neuron detects uncommon or rare proper names (unfamiliar named entities) in the text.

    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
     fort
    -0.06
     rendering
    -0.06
    STM
    -0.06
     benchmark
    -0.06
     Заг
    -0.05
    	TEST
    -0.05
    atisation
    -0.05
     заг
    -0.05
     FTP
    -0.05
     acceleration
    -0.05
    POSITIVE LOGITS
    ikal
    0.07
     üz
    0.07
    回来
    0.07
    _,,
    0.07
     Marl
    0.07
    混
    0.07
     reloadData
    0.07
    ListComponent
    0.07
     Moines
    0.07
     »
    0.07
    Activations Density 0.201%

    No Known Activations