© 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. 109151
    Prev
    Next
    INDEX
    Explanations

    These

    np_max-act · gemini-2.0-flash

    This neuron activates on the common “closing‐summary” phrase at the end of list answers, e.g. “These are just a few of ….”

    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
     NT
    -0.07
     fails
    -0.06
     defence
    -0.06
     persisted
    -0.06
    _order
    -0.06
     raced
    -0.06
     uni
    -0.06
    mrt
    -0.06
     subclasses
    -0.06
    .StObject
    -0.06
    POSITIVE LOGITS
    _qos
    0.07
    kili
    0.07
    _publish
    0.07
    /plugin
    0.06
     Duis
    0.06
    固
    0.06
    NECT
    0.06
     Sinatra
    0.06
    emoc
    0.06
    lecture
    0.06
    Activations Density 0.034%

    No Known Activations