© 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. 58555
    Prev
    Next
    INDEX
    Explanations

    beach

    np_max-act · gemini-2.0-flash

    This neuron activates on words related to seaside or beach resorts (e.g. Italian “località balneare” and “spiagge”).

    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
     picture
    -0.07
    (Calendar
    -0.06
    	stream
    -0.06
     surrender
    -0.06
     世界
    -0.06
     totaled
    -0.06
    ded
    -0.06
    .cart
    -0.06
     Already
    -0.06
     Salv
    -0.06
    POSITIVE LOGITS
    tabl
    0.07
    ęk
    0.06
     Toe
    0.06
     SQLITE
    0.06
    ynn
    0.06
    portun
    0.06
    ागत
    0.06
    设计器
    0.06
     beaches
    0.06
    88
    0.06
    Activations Density 0.012%

    No Known Activations