© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59168
    Prev
    Next
    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash

    The neuron is sensitive to technical terminology related to data‐based wireless communications (e.g. “packet,” “data,” “network,” “radio,” “mobile,” “service,” “digital”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     infamous
    -0.07
     jež
    -0.07
    ertura
    -0.06
    лен
    -0.06
     모
    -0.06
     Christoph
    -0.06
    ICI
    -0.06
    Neil
    -0.06
    DIRECTORY
    -0.06
    temperature
    -0.06
    POSITIVE LOGITS
     nbr
    0.07
    .lazy
    0.07
    惊
    0.06
    Queries
    0.06
    Coming
    0.06
     Booster
    0.06
     Graves
    0.06
    Processed
    0.06
     Superv
    0.06
    .getProduct
    0.06
    Activations Density 0.007%

    No Known Activations