© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 108717
    Prev
    Next
    INDEX
    Explanations

    originals

    np_max-act · gemini-2.0-flash

    This neuron is sensitive to numeric tokens and related units, i.e. it activates on numbers, measurements, dates, and quantities.

    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
     Буд
    -0.07
    Courtesy
    -0.07
     contender
    -0.07
     quits
    -0.07
    Fetch
    -0.07
    vim
    -0.07
     texas
    -0.07
    standing
    -0.07
     philippines
    -0.07
    -pointer
    -0.07
    POSITIVE LOGITS
    latable
    0.07
     zásob
    0.06
     [];
↵
    0.06
     Vác
    0.06
    تح
    0.06
     "]";↵
    0.06
    ‌شوند
    0.06
     توسط
    0.06
    )];↵↵
    0.06
     einmal
    0.06
    Activations Density 0.158%

    No Known Activations