© 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. 12488
    Prev
    Next
    INDEX
    Explanations

    customer service

    np_max-act · gemini-2.0-flash

    The neuron detects terminology related to classifying a customer’s intent—words like “category,” “intention,” “code,” and similar instruction cues.

    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
    صول
    -0.07
    Init
    -0.07
    Trees
    -0.07
     Realty
    -0.07
    _configuration
    -0.07
     Zion
    -0.07
    INCREMENT
    -0.06
    -dollar
    -0.06
    ensa
    -0.06
    gmail
    -0.06
    POSITIVE LOGITS
    "]]↵
    0.07
    ("+
    0.07
    lovak
    0.06
     opsiyon
    0.06
    _LT
    0.06
    >\↵
    0.06
    ◎
    0.06
    ξε
    0.06
    지노
    0.06
     uydu
    0.06
    Activations Density 0.009%

    No Known Activations