© 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. 58042
    Prev
    Next
    INDEX
    Explanations

    food ingredients

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of cooking methods and flavor‐enhancing ingredients (e.g. roasted, lemon, garlic, sauce, herbs) in recipe descriptions.

    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
    jour
    -0.07
    (["
    -0.07
    �
    -0.07
     �
    -0.07
    IZATION
    -0.07
    (['
    -0.07
    conda
    -0.06
    忙
    -0.06
    ерами
    -0.06
    ivatel
    -0.06
    POSITIVE LOGITS
     "../../../../
    0.07
     childs
    0.07
    SC
    0.06
     opcode
    0.06
     occasions
    0.06
    plug
    0.06
     případech
    0.06
     aimed
    0.06
     Hemisphere
    0.06
    -overlay
    0.06
    Activations Density 0.020%

    No Known Activations