© 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. 127010
    Prev
    Next
    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash

    This neuron fires on tokens describing a scene of someone seated (e.g. “bench,” “park”)—i.e. it detects when a character is sitting on a bench in a park.

    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
     Mes
    -0.06
    (wait
    -0.06
     principles
    -0.06
    Wonder
    -0.06
     captivity
    -0.06
     alkal
    -0.06
     explo
    -0.06
     Agility
    -0.06
    creasing
    -0.06
    _pres
    -0.06
    POSITIVE LOGITS
    ::_
    0.07
    _HW
    0.06
    しの
    0.06
     때
    0.06
    μει
    0.06
    stants
    0.06
     desks
    0.06
    >
↵
↵
↵
    0.06
    ندق
    0.06
    aside
    0.06
    Activations Density 0.048%

    No Known Activations