© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59277
    Prev
    Next
    INDEX
    Explanations

    math calculations

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric tokens—digits, decimal numbers, and other numeral forms.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    isd
    -0.07
    legant
    -0.06
    alık
    -0.06
    ivé
    -0.06
     transit
    -0.06
    Œ
    -0.06
     isAdmin
    -0.06
    elles
    -0.06
    [Int
    -0.06
    calcul
    -0.06
    POSITIVE LOGITS
     gleich
    0.07
     attempting
    0.07
    후
    0.06
    THEN
    0.06
    .Serialize
    0.06
     Hawaiian
    0.06
     chests
    0.06
     Например
    0.06
     arkadaş
    0.06
     Jes
    0.06
    Activations Density 0.009%

    No Known Activations