© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30424
    Prev
    Next
    INDEX
    Explanations

    negation

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on numeric expressions (digits, decimals, measurements, percentages), i.e. quantitative tokens.

    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
     Dollars
    -0.07
    /commons
    -0.07
    metry
    -0.07
    :\"
    -0.06
    fork
    -0.06
     influ
    -0.06
    ää
    -0.06
     MONEY
    -0.06
    ailles
    -0.06
     Lesser
    -0.06
    POSITIVE LOGITS
     الآ
    0.07
     لف
    0.06
    ніш
    0.06
    (btn
    0.06
     ها
    0.06
     escalated
    0.06
    علومات
    0.06
     그래서
    0.06
    GAN
    0.06
     текст
    0.06
    Activations Density 0.037%

    No Known Activations