© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 73867
    Prev
    Next
    INDEX
    Explanations

    interactions

    np_max-act · gemini-2.0-flash

    This neuron activates on function words in context-setting prepositional/subordinate phrases (e.g. “when,” “in,” “of,” “company,” “fellow,” “around”) that introduce circumstances or situations.

    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
     cabbage
    -0.06
     cling
    -0.06
    .annotate
    -0.06
     béné
    -0.06
    [root
    -0.06
    око
    -0.06
     pairwise
    -0.06
     unprecedented
    -0.06
     Jordan
    -0.05
     Kristen
    -0.05
    POSITIVE LOGITS
     acción
    0.07
     Cơ
    0.07
    ặc
    0.06
    าประ
    0.06
     kaynak
    0.06
    _thickness
    0.06
    uvian
    0.06
    steder
    0.06
    IER
    0.06
    -spinner
    0.06
    Activations Density 0.039%

    No Known Activations