© 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. 90574
    Prev
    Next
    INDEX
    Explanations

    code, variables, parameters

    np_max-act · gemini-2.0-flash

    The neuron detects expressions where a “name” field is compared to a literal (e.g. name = 'Tom' or name === text).

    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
     ApiService
    -0.07
    众
    -0.07
     Town
    -0.06
     count
    -0.06
    Jones
    -0.06
    得
    -0.06
     directs
    -0.06
    ere
    -0.06
    หมด
    -0.06
     одне
    -0.06
    POSITIVE LOGITS
     funcion
    0.06
     dequeue
    0.06
    Permanent
    0.06
     CRM
    0.06
    ,—
    0.06
     लक
    0.06
    очка
    0.06
     �
    0.06
     Navigate
    0.06
     Napoli
    0.06
    Activations Density 0.029%

    No Known Activations