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

    Neuronpedia

    Jacobian LensNEW
    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. 38229
    Prev
    Next
    INDEX
    Explanations

    few

    np_max-act · gemini-2.0-flash

    This neuron is activated by the quantifier “few” (and its variants like “fewer”) indicating a small number or amount.

    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
    Mark
    -0.07
    concat
    -0.06
     Handles
    -0.06
    -fold
    -0.06
     automáticamente
    -0.06
     latch
    -0.06
    restaurant
    -0.06
     ENERGY
    -0.06
     AMAZ
    -0.06
     super
    -0.06
    POSITIVE LOGITS
    Few
    0.12
     Few
    0.11
     fewer
    0.11
     few
    0.10
     rarely
    0.08
    ↵↵
    0.08
    IQ
    0.07
     Fou
    0.07
     dbContext
    0.07
     Low
    0.07
    Activations Density 0.014%

    No Known Activations