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

    Neuronpedia

    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. 7445
    Prev
    Next
    INDEX
    Explanations

    quotation marks/brackets

    np_max-act · gemini-2.0-flash

    This neuron detects JSON field names and keywords used in Elasticsearch’s DSL (e.g. “mappings”, “query”, “bool”, “match”, “range”, etc.).

    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
     Machine
    -0.07
     types
    -0.07
     deviation
    -0.07
     sensors
    -0.07
     Inspired
    -0.07
    Exit
    -0.06
     across
    -0.06
     Pan
    -0.06
     species
    -0.06
     type
    -0.06
    POSITIVE LOGITS
    .charAt
    0.06
    'It
    0.06
    -item
    0.06
     entitled
    0.06
    .MIN
    0.06
     ー
    0.06
     θα
    0.06
     натураль
    0.06
    573
    0.06
     фар
    0.06
    Activations Density 0.042%

    No Known Activations