© 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
    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. 9177
    Prev
    Next
    INDEX
    Explanations

    grief and difficult experiences

    np_max-act · gemini-2.0-flash

    This neuron spots mentions of family members or close caregivers (e.g. siblings, family, friends) and related psychosocial support contexts.

    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
     Herman
    -0.06
     Marks
    -0.06
     fds
    -0.06
    Ark
    -0.06
    DataURL
    -0.06
     Holt
    -0.06
     radiation
    -0.06
     cosmetic
    -0.06
     showers
    -0.06
    ล
    -0.06
    POSITIVE LOGITS
    .trailing
    0.07
     nebude
    0.07
    migration
    0.06
     mí
    0.06
    ________________________________________________________________
    0.06
     &___
    0.06
    وست
    0.06
     чувств
    0.06
    actus
    0.06
    \TestCase
    0.06
    Activations Density 0.051%

    No Known Activations