Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126448
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    This neuron detects opening parenthesis characters “(” marking parenthetical asides.

    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
    	QString
    -0.06
     звіль
    -0.06
     موضوع
    -0.06
    	com
    -0.06
    ύτε
    -0.06
     Warner
    -0.06
     Matcher
    -0.06
     بگ
    -0.06
     Patton
    -0.06
    �
    -0.05
    POSITIVE LOGITS
    Cal
    0.07
    dıkları
    0.07
    igram
    0.07
    minate
    0.06
    yellow
    0.06
    atchewan
    0.06
     ox
    0.06
     boast
    0.06
    ucked
    0.06
     Banking
    0.06
    Activations Density 0.002%

    No Known Activations