© 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. 38968
    Prev
    Next
    INDEX
    Explanations

    ba

    np_max-act · gemini-2.0-flash

    This neuron responds to specialized Sanskrit or ritual terms associated with Hindu festival ceremonies (e.g. puja, vrat, Bhadrapada, vastra).

    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
    ALL
    -0.08
    up
    -0.07
    ÓN
    -0.07
    姫
    -0.07
    зь
    -0.07
    8
    -0.07
    ANT
    -0.07
    op
    -0.07
    üğ
    -0.07
    redd
    -0.07
    POSITIVE LOGITS
     Sa
    0.09
    Sa
    0.08
     fa
    0.08
     ma
    0.07
     Fe
    0.07
    itime
    0.07
     Hà
    0.07
    fa
    0.07
     Ma
    0.07
     Bailey
    0.07
    Activations Density 0.275%

    No Known Activations