© 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. 65222
    Prev
    Next
    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash

    The neuron fires on named entities—proper nouns like event names, titles, and people’s names.

    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
    FetchRequest
    -0.06
    Launcher
    -0.06
     Rays
    -0.06
     Guidelines
    -0.06
    Interfaces
    -0.06
    ��
    -0.06
    retim
    -0.06
    .sprites
    -0.05
    вий
    -0.05
    -am
    -0.05
    POSITIVE LOGITS
     Ebola
    0.07
     хвор
    0.07
     below
    0.07
     Altın
    0.07
    NSURLSession
    0.07
    بور
    0.07
    κει
    0.07
    lun
    0.06
     Vacc
    0.06
     HOST
    0.06
    Activations Density 0.364%

    No Known Activations