© 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. 6906
    Prev
    Next
    INDEX
    Explanations

    sporting events

    np_max-act · gemini-2.0-flash

    The neuron activates on words and phrases related to sports competitions and events (e.g. championships, Olympic entries, demonstration sports, match types).

    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
    共和国
    -0.07
    ezi
    -0.06
     Tank
    -0.06
     sparked
    -0.06
    را
    -0.06
     서비스
    -0.06
     Eventually
    -0.06
     сал
    -0.06
     thi
    -0.06
     cone
    -0.06
    POSITIVE LOGITS
    สาย
    0.07
     bree
    0.07
    域
    0.06
     Sears
    0.06
     Дата
    0.06
     下载
    0.06
     Scient
    0.06
     ﾚ
    0.06
     segreg
    0.06
    出品
    0.06
    Activations Density 0.156%

    No Known Activations