© 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. 54423
    Prev
    Next
    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    This neuron detects mention of a project’s provenance—tokens indicating it’s “open-source,” and verbs like “was developed by” and related author/maintainer information.

    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
    _align
    -0.08
     aplicación
    -0.07
     겁
    -0.07
     GST
    -0.06
    '''
    -0.06
    seconds
    -0.06
    洞
    -0.06
    (null
    -0.06
     segundos
    -0.06
    ieten
    -0.06
    POSITIVE LOGITS
    immer
    0.07
     ž
    0.07
    immers
    0.07
     fortunate
    0.06
     veren
    0.06
     Shr
    0.06
    -found
    0.06
    Dispatcher
    0.06
     अख
    0.06
     Lect
    0.06
    Activations Density 0.027%

    No Known Activations