© 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. 56221
    Prev
    Next
    INDEX
    Explanations

    question

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of “question” (and its variants like “questions” or “questionnaire”), i.e. references to survey questions or question items.

    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
    740
    -0.08
    _WORK
    -0.07
     spray
    -0.07
     hd
    -0.06
     перест
    -0.06
     Pé
    -0.06
    /id
    -0.06
     zien
    -0.06
    buch
    -0.06
     reboot
    -0.06
    POSITIVE LOGITS
     constructions
    0.07
     Restricted
    0.07
    ัญห
    0.07
    instructions
    0.06
    기는
    0.06
    있는
    0.06
     deluxe
    0.06
    Express
    0.06
    协议
    0.06
     Sergey
    0.06
    Activations Density 0.007%

    No Known Activations