© 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
    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. 74073
    Prev
    Next
    INDEX
    Explanations

    question

    np_max-act · gemini-2.0-flash

    The neuron activates on words and phrases that introduce or label questions or instructions (e.g. “question,” “riddle,” “first,” “third,” “quiz”).

    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
    الح
    -0.07
    283
    -0.06
    -real
    -0.06
    LEGAL
    -0.06
    getLast
    -0.06
     Mar
    -0.06
    V
    -0.06
    payload
    -0.06
    /tool
    -0.06
    migration
    -0.06
    POSITIVE LOGITS
    _warning
    0.07
     "),↵
    0.06
    Given
    0.06
    .ClientSize
    0.06
     determin
    0.06
    .protobuf
    0.06
    duğunu
    0.06
    <w
    0.06
     Uncle
    0.06
     Hen
    0.06
    Activations Density 0.011%

    No Known Activations