© 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. 30761
    Prev
    Next
    INDEX
    Explanations

    Different languages

    np_max-act · gemini-2.0-flash

    The neuron predominantly responds to subword tokens containing non‐standard Latin characters or diacritics, effectively flagging foreign/accents-laden text.

    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
     zIndex
    -0.08
     MAP
    -0.07
     Paramount
    -0.07
     ERROR
    -0.06
    平方公里
    -0.06
    _test
    -0.06
     작품
    -0.06
    CHASE
    -0.06
     karak
    -0.06
     unwrap
    -0.06
    POSITIVE LOGITS
    trag
    0.07
    رب
    0.06
     indonesia
    0.06
     Ent
    0.06
    `](
    0.06
     guarantee
    0.06
    181
    0.06
     Prom
    0.06
    uous
    0.06
     disciplines
    0.06
    Activations Density 0.032%

    No Known Activations