© 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. 90803
    Prev
    Next
    INDEX
    Explanations

    nam

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the country name “Vietnam” (i.e. the subword tokens “Viet” and “nam”).

    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
    追加
    -0.07
     disruptive
    -0.06
    počet
    -0.06
     detergent
    -0.06
     Falk
    -0.06
    штов
    -0.06
    innerText
    -0.06
    bson
    -0.06
     morb
    -0.06
    ウス
    -0.06
    POSITIVE LOGITS
     Vietnam
    0.13
    Viet
    0.09
     Viet
    0.09
     Vietnamese
    0.08
     gmail
    0.07
    anoi
    0.07
     Nguyen
    0.07
     Việt
    0.07
    .vn
    0.07
    /QĐ
    0.06
    Activations Density 0.016%

    No Known Activations