© 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 EvalsExportsinterp-engineNEWAPI 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. 58790
    Prev
    Next
    INDEX
    Explanations

    Imaginative play

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of specific children’s toys and play items (e.g. building blocks, LEGO sets, play-sets, educational toys).

    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
    �
    -0.07
    ��이
    -0.06
     <:
    -0.06
     چه
    -0.06
    agas
    -0.06
    าเล
    -0.06
    .localized
    -0.06
    .activity
    -0.06
     बस
    -0.06
    .Framework
    -0.06
    POSITIVE LOGITS
     tête
    0.06
     прок
    0.06
     episodes
    0.06
     WX
    0.06
     команди
    0.06
    ,GL
    0.06
     DRAW
    0.06
     Rolex
    0.06
    umpy
    0.06
    rieben
    0.06
    Activations Density 0.029%

    No Known Activations