Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 85973
    Prev
    Next
    INDEX
    Explanations

    user interface code

    np_max-act · gemini-2.0-flash

    The neuron specifically fires on the Ukrainian word “завантаження” (and its forms), i.e. occurrences of the term for “loading.”

    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
    人类
    -0.07
    _costs
    -0.06
    مح
    -0.06
     Seats
    -0.06
    ensible
    -0.06
    _ENT
    -0.06
    価
    -0.06
    _abs
    -0.06
    _sentences
    -0.06
    aking
    -0.06
    POSITIVE LOGITS
    "urls
    0.07
     Shanghai
    0.06
     ArrayAdapter
    0.06
     Locale
    0.06
    tank
    0.06
     assuming
    0.06
     Ea
    0.06
     :</
    0.06
    assign
    0.06
     ler
    0.06
    Activations Density 0.057%

    No Known Activations