© 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 EvalsExportsinterp-engineNEWAPI 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. 58320
    Prev
    Next
    INDEX
    Explanations

    Origins of political entities

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens and date expressions, flagging years and other numbers in historical or informational contexts.

    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
     conosc
    -0.07
    .tw
    -0.07
     persön
    -0.06
    ْح
    -0.06
     timely
    -0.06
    香港
    -0.06
    uhe
    -0.06
    자료
    -0.06
     confused
    -0.06
     manufacturer
    -0.06
    POSITIVE LOGITS
     yönetim
    0.07
     dostan
    0.06
    vailable
    0.06
     $_[
    0.06
    .answers
    0.06
    ----↵
    0.06
     pil
    0.06
     cil
    0.06
    IMITER
    0.06
    (parseFloat
    0.06
    Activations Density 0.020%

    No Known Activations