© 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. 91295
    Prev
    Next
    INDEX
    Explanations

    applications

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of streaming‐related activities—e.g. “stream,” “streams,” and “content” in a streaming/context-creation context.

    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
     الك
    -0.07
    dot
    -0.07
     tween
    -0.07
     lx
    -0.06
    asured
    -0.06
     witch
    -0.06
     rů
    -0.06
     برگز
    -0.06
    Danny
    -0.06
     dragon
    -0.06
    POSITIVE LOGITS
    ��
    0.07
    ąd
    0.06
    ouv
    0.06
     hesab
    0.06
     زمانی
    0.06
     lasc
    0.06
    cha
    0.06
    	ft
    0.06
    ceive
    0.06
    kept
    0.06
    Activations Density 0.165%

    No Known Activations