© 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. 124941
    Prev
    Next
    INDEX
    Explanations

    glory

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of “glorify” (and its variants like “glorification”), i.e. language that explicitly praises or exalts something.

    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
     insect
    -0.07
    algorithm
    -0.07
    Checksum
    -0.07
    scan
    -0.07
    吸
    -0.06
     perpetrator
    -0.06
     ten
    -0.06
     Noah
    -0.06
     nik
    -0.06
    _note
    -0.06
    POSITIVE LOGITS
     Glory
    0.12
     glory
    0.12
     glamorous
    0.10
     glorious
    0.09
     glamour
    0.08
     glor
    0.08
    glomer
    0.07
    将
    0.07
     قرار
    0.07
    gl
    0.07
    Activations Density 0.005%

    No Known Activations