© 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. 108925
    Prev
    Next
    INDEX
    Explanations

    ASKING_QUESTIONS

    np_max-act · gemini-2.0-flash

    The neuron fires on interrogative question words (and related tokens), i.e. it detects the presence of question-opening words like “How,” “Which,” “What,” “Who,” “Do,” etc., (and the question mark) in user queries.

    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
    Adobe
    -0.06
    -webpack
    -0.06
     Entries
    -0.06
     Vote
    -0.06
    ağın
    -0.06
     chops
    -0.06
    ece
    -0.06
     nip
    -0.06
     head
    -0.06
     Baba
    -0.06
    POSITIVE LOGITS
    .modelo
    0.07
    wap
    0.07
    iami
    0.06
    visející
    0.06
    ,omitempty
    0.06
    ๊ก
    0.06
    .party
    0.06
     Huckabee
    0.06
    _contin
    0.06
    REDIS
    0.06
    Activations Density 0.029%

    No Known Activations