© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91977
    Prev
    Next
    INDEX
    Explanations

    procedural

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on terms describing roguelike and procedural‐generation features (e.g. “rogue‐like,” “procedural”).

    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
    .player
    -0.07
    姊
    -0.06
     Bookmark
    -0.06
    .signup
    -0.06
    .SimpleButton
    -0.06
     لم
    -0.06
     Fighter
    -0.06
     doll
    -0.06
     baker
    -0.06
     '+
    -0.06
    POSITIVE LOGITS
    latesAutoresizingMaskIntoConstraints
    0.06
    增长
    0.06
    fillType
    0.06
     Gson
    0.06
     HY
    0.06
     hilar
    0.06
     PCA
    0.06
     Backpack
    0.06
    ιστή
    0.06
     exper
    0.06
    Activations Density 0.008%

    No Known Activations