© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 92113
    Prev
    Next
    INDEX
    Explanations

    grammar

    np_max-act · gemini-2.0-flash

    This neuron detects grammatical-category labels—especially phrases like “specific noun,” “mass noun,” “count noun,” 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
     bartender
    -0.06
     Site
    -0.06
     BJP
    -0.06
     shirt
    -0.06
     (::
    -0.06
    EEDED
    -0.06
    stop
    -0.06
     pound
    -0.06
     米
    -0.06
     S
    -0.05
    POSITIVE LOGITS
    вит
    0.06
    pf
    0.06
    lop
    0.06
    ины
    0.06
    _Service
    0.06
    لة
    0.06
     मज
    0.06
     rempl
    0.06
    Elect
    0.06
     		↵
    0.06
    Activations Density 0.028%

    No Known Activations