© 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. 110666
    Prev
    Next
    INDEX
    Explanations

    personal stories

    np_max-act · gemini-2.0-flash

    The neuron is primarily detecting self-referential language, especially first-person pronouns and expressions of personal experience or belief (e.g. “I,” “my,” “believe,” “think”).

    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
    -syntax
    -0.08
     '/
    -0.07
    الات
    -0.06
     backs
    -0.06
    @Path
    -0.06
     quadratic
    -0.06
     startups
    -0.06
     对
    -0.06
     ValidationResult
    -0.06
    ")){↵
    -0.06
    POSITIVE LOGITS
    VAR
    0.07
     Böl
    0.06
    (render
    0.06
     extinction
    0.06
    ілля
    0.06
    .fasterxml
    0.06
    ordin
    0.06
     getDate
    0.06
     rozvoj
    0.06
    ً
    0.06
    Activations Density 0.089%

    No Known Activations