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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110701
    Prev
    Next
    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash

    The neuron detects descriptions of data‐storage operations and memory device behavior—mentions of storing, retaining, reading, or writing data/information.

    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
     swallowing
    -0.07
     uploading
    -0.06
    GGLE
    -0.06
     honestly
    -0.06
     organization
    -0.06
     nour
    -0.06
    (blocks
    -0.06
    Sorting
    -0.06
    withdraw
    -0.06
    we
    -0.06
    POSITIVE LOGITS
     Kiev
    0.07
    .uint
    0.07
     Albums
    0.07
    genus
    0.07
    girl
    0.07
     naughty
    0.06
    /self
    0.06
     Caj
    0.06
    abar
    0.06
    .|
    0.06
    Activations Density 0.014%

    No Known Activations