© 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. 110518
    Prev
    Next
    INDEX
    Explanations

    first person stories

    np_max-act · gemini-2.0-flash

    This neuron fires on first-person self-references (e.g. “I,” “me,” “my”), picking out passages where the author speaks in the first person.

    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
    InBackground
    -0.07
    HeaderInSection
    -0.07
    executable
    -0.07
     Hz
    -0.06
    雲
    -0.06
    ierarchy
    -0.06
    editing
    -0.06
    igure
    -0.06
     reasonably
    -0.06
     AnyObject
    -0.06
    POSITIVE LOGITS
     I
    0.08
     Finished
    0.07
    實
    0.07
     granite
    0.06
     device
    0.06
     entirety
    0.06
     relinqu
    0.06
    گاهی
    0.06
     Trip
    0.06
     absorbed
    0.06
    Activations Density 0.097%

    No Known Activations