© 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. 6039
    Prev
    Next
    INDEX
    Explanations

    amos

    np_max-act · gemini-2.0-flash

    The neuron is selectively activated by tokens written in non-Latin scripts (e.g. Hebrew, Cyrillic or other accented/foreign characters), i.e. it detects non-English/Latin text.

    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
     but
    -0.09
     bet
    -0.08
    but
    -0.08
     SORT
    -0.08
     inte
    -0.07
     viewpoint
    -0.07
    	that
    -0.07
     If
    -0.07
     string
    -0.07
     drawing
    -0.06
    POSITIVE LOGITS
    λικ
    0.07
    acellular
    0.07
     Ive
    0.07
    osl
    0.07
    ych
    0.07
    baru
    0.07
    ینی
    0.06
    mür
    0.06
    ประถม
    0.06
     ГО
    0.06
    Activations Density 0.090%

    No Known Activations