© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91918
    Prev
    Next
    INDEX
    Explanations

    Sports leagues and teams

    np_max-act · gemini-2.0-flash

    The neuron activates on names of sports teams or clubs (proper‐noun multiword team names).

    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
    위원회
    -0.07
    ponsor
    -0.07
    aben
    -0.07
     Paginator
    -0.06
    orpion
    -0.06
    _seg
    -0.06
     transplantation
    -0.06
    ourced
    -0.06
     angrily
    -0.06
     destabil
    -0.06
    POSITIVE LOGITS
    ラー
    0.06
    NAV
    0.06
     earning
    0.06
     Feeling
    0.06
     jon
    0.06
     MutableLiveData
    0.06
     Mellon
    0.06
    ematik
    0.06
    ้ร
    0.06
     \
    0.06
    Activations Density 0.031%

    No Known Activations