© 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. 59308
    Prev
    Next
    INDEX
    Explanations

    indoor locations

    np_max-act · gemini-2.0-flash

    This neuron activates on words naming physical locations (e.g. rooms or places) in the text.

    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
     CENTER
    -0.07
     systems
    -0.07
     officials
    -0.06
    (ele
    -0.06
    重複重複
    -0.06
     Ferrari
    -0.06
    無し�
    -0.06
     talents
    -0.06
    Selective
    -0.06
     Discount
    -0.06
    POSITIVE LOGITS
    .↵
    0.07
    빈
    0.07
    acket
    0.06
    .↵
    0.06
    .
    0.06
     Steelers
    0.06
    ısıt
    0.06
    lime
    0.06
       ↵
    0.06
    ()."
    0.06
    Activations Density 0.007%

    No Known Activations