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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 38179
    Prev
    Next
    INDEX
    Explanations

    Thoughts and opinions

    np_max-act · gemini-2.0-flash

    The neuron fires on idiomatic expressions that mean “you’ve just said exactly what I was thinking,” such as “you took the words out of my mouth” or “you read my mind.”

    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
     forCell
    -0.06
    orris
    -0.06
     Knight
    -0.06
    :'#
    -0.06
     xhr
    -0.06
    _CIPHER
    -0.06
     legion
    -0.06
     Newark
    -0.06
     nuevos
    -0.06
    งเป
    -0.06
    POSITIVE LOGITS
     minim
    0.06
    ).^
    0.06
     cryptographic
    0.06
    出
    0.06
     ATTACK
    0.06
     Alcohol
    0.06
     Họ
    0.06
    Guest
    0.06
     arrest
    0.06
     PropertyInfo
    0.06
    Activations Density 0.044%

    No Known Activations