© 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. 38022
    Prev
    Next
    INDEX
    Explanations

    medieval

    np_max-act · gemini-2.0-flash

    This neuron specifically detects occurrences of the word “medieval,” i.e. references to the medieval period.

    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
    QueryString
    -0.07
    upiter
    -0.07
    άλι
    -0.07
    unami
    -0.06
     Star
    -0.06
    Histogram
    -0.06
     pundits
    -0.06
     Cove
    -0.06
     proyecto
    -0.06
     큰
    -0.06
    POSITIVE LOGITS
     medieval
    0.12
     Medieval
    0.11
    ieval
    0.08
    §
    0.07
     tekn
    0.06
    ORAGE
    0.06
    Tenant
    0.06
     thiểu
    0.06
     �
    0.06
    OLF
    0.06
    Activations Density 0.003%

    No Known Activations