© 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. 13889
    Prev
    Next
    INDEX
    Explanations

    perspective, point of view

    np_max-act · gemini-2.0-flash

    This neuron lights up on high‐frequency English function words (especially pronouns and auxiliaries like “I,” “you,” “if,” “The,” etc.).

    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
     Slider
    -0.06
     xa
    -0.06
    ortality
    -0.06
    Disconnect
    -0.06
    .attribute
    -0.06
    ้ค
    -0.06
     Supplements
    -0.06
    utta
    -0.06
     террит
    -0.06
    .completed
    -0.06
    POSITIVE LOGITS
     SNAP
    0.06
     Fucking
    0.06
    .Abstract
    0.06
    нему
    0.06
    国家
    0.06
     chickens
    0.06
     Arbor
    0.06
    ',['
    0.06
    .decorators
    0.06
      ↵
    0.06
    Activations Density 0.053%

    No Known Activations