© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 8777
    Prev
    Next
    INDEX
    Explanations

    sentence structures

    np_max-act · gemini-2.0-flash

    This neuron is sensitive to title‐style or proper‐name tokens, i.e. capitalized words used in headings, show names, episode titles, and other named entities.

    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
     seizure
    -0.06
    SELF
    -0.06
    �다
    -0.06
     specializes
    -0.06
    //================================================================================
    -0.06
    ализации
    -0.06
     grandmother
    -0.06
    leDb
    -0.06
    處
    -0.06
     tweeted
    -0.06
    POSITIVE LOGITS
    );?>↵
    0.06
     Deb
    0.06
    zí
    0.06
    _arc
    0.06
    	   ↵
    0.06
    ียวก
    0.06
    (std
    0.06
    _New
    0.06
     जनत
    0.06
     прик
    0.06
    Activations Density 0.033%

    No Known Activations