© 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. 91444
    Prev
    Next
    INDEX
    Explanations

    Thinking/calculation

    np_max-act · gemini-2.0-flash

    The neuron detects “chain‐of‐thought” prompt language—phrases like “think … step by step.”

    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
    .faceVertexUvs
    -0.07
    icts
    -0.07
    -turn
    -0.07
    规范
    -0.07
    Playlist
    -0.06
     распрост
    -0.06
     enn
    -0.06
    ி
    -0.06
    层
    -0.06
    进一步
    -0.06
    POSITIVE LOGITS
     Hang
    0.06
     Sexual
    0.06
     eb
    0.06
     relação
    0.06
    (dynamic
    0.06
     yolc
    0.06
     Sergio
    0.06
         
    0.06
    ンス
    0.06
     Pot
    0.06
    Activations Density 0.002%

    No Known Activations