© 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. 91240
    Prev
    Next
    INDEX
    Explanations

    "to be" verb forms

    np_max-act · gemini-2.0-flash

    The neuron fires on third-person narrative constructions—especially pronouns like “he,” “she,” or “they” paired with copulas (e.g. “was,” “were”) in descriptive storytelling.

    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
     Prep
    -0.07
    459
    -0.06
     WEST
    -0.06
     fluffy
    -0.06
    形式
    -0.06
    Tick
    -0.06
    852
    -0.05
    Alternative
    -0.05
    WOOD
    -0.05
    546
    -0.05
    POSITIVE LOGITS
     fanc
    0.06
     slun
    0.06
     pastors
    0.06
    (Local
    0.06
     Uttar
    0.06
     sentinel
    0.06
     мала
    0.06
     alguns
    0.06
     attempting
    0.06
    نب
    0.06
    Activations Density 0.137%

    No Known Activations