© 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. 54234
    Prev
    Next
    INDEX
    Explanations

    bilingual

    np_max-act · gemini-2.0-flash

    The neuron strongly fires on the term “bilingual” (and its variants like “bilingualism”), effectively detecting mentions of bilingualism.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    terms related to bilingualism and linguistic studies, particularly focusing on cognitive and educational aspects.

    oai_token-act-pair · gpt-4o-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
     decks
    -0.07
    チェ
    -0.07
    _audit
    -0.07
     Ranger
    -0.06
    argent
    -0.06
     ":"
    -0.06
     mücadele
    -0.06
     verschiedenen
    -0.06
     area
    -0.06
     MAT
    -0.06
    POSITIVE LOGITS
    ilingual
    0.08
     bilingual
    0.08
     null
    0.07
    orio
    0.06
    ><?
    0.06
    mother
    0.06
    composed
    0.06
    inburgh
    0.06
    йте
    0.06
    (guid
    0.06
    Activations Density 0.002%

    No Known Activations