© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 13668
    Prev
    Next
    INDEX
    Explanations

    stay

    np_max-act · gemini-2.0-flash

    The neuron detects words that express remaining in a state (e.g., “stay,” “permanently”).

    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
     entry
    -0.07
    ۵
    -0.06
    Specifies
    -0.06
    -Men
    -0.06
    投資
    -0.06
    otional
    -0.06
    bles
    -0.06
    sequent
    -0.06
     assembly
    -0.06
    ские
    -0.06
    POSITIVE LOGITS
     stay
    0.11
     staying
    0.10
     stayed
    0.09
     remain
    0.09
     remained
    0.08
     stays
    0.08
    监听页面
    0.07
     Stay
    0.07
    Demo
    0.07
     Vaccine
    0.07
    Activations Density 0.028%

    No Known Activations