© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 128702
    Prev
    Next
    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash

    This neuron detects words and phrases that describe formal or official actions—calls, requests, orders, plans, or policy proposals—typically by government or organizational bodies.

    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
     Dim
    -0.07
    医学
    -0.06
    legend
    -0.06
     intensity
    -0.06
     POWER
    -0.06
    _dicts
    -0.06
    Customer
    -0.06
     Pa
    -0.06
     молод
    -0.06
     Casting
    -0.06
    POSITIVE LOGITS
    PictureBox
    0.07
    xCB
    0.07
    getDefault
    0.06
     stad
    0.06
    **↵↵
    0.06
     rej
    0.06
     {
↵
    0.06
    és
    0.06
    .Enable
    0.06
    (det
    0.06
    Activations Density 0.099%

    No Known Activations