© 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. 110168
    Prev
    Next
    INDEX
    Explanations

    ipay

    np_max-act · gemini-2.0-flash

    The neuron activates whenever it sees the substring “ipay” (as in “Alipay”) in identifiers.

    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
    ]string
    -0.07
     入
    -0.06
     лег
    -0.06
    媒体
    -0.06
     привы
    -0.06
     Cool
    -0.06
     wireType
    -0.06
    .sol
    -0.06
    (uri
    -0.06
     breakfast
    -0.06
    POSITIVE LOGITS
     gaz
    0.07
    ,var
    0.07
    chalk
    0.06
     spikes
    0.06
    ulan
    0.06
    -independent
    0.06
    Chinese
    0.06
    ,output
    0.06
    inz
    0.06
    anged
    0.06
    Activations Density 0.001%

    No Known Activations