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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 79402
    Prev
    Next
    INDEX
    Explanations

    Ancestors

    np_max-act · gemini-2.0-flash

    references to family lineage and generational ties.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects mentions of extended family relationships marked by repeated “great”/“grand” tokens (e.g. great-grandfather, great-uncle, great-grandson).

    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
    彼
    -0.07
    URLOPT
    -0.07
    .AlertDialog
    -0.07
     shrink
    -0.07
    alone
    -0.06
    イント
    -0.06
    かる
    -0.06
     sd
    -0.06
    _cpus
    -0.06
     NK
    -0.06
    POSITIVE LOGITS
     workshops
    0.06
    .def
    0.06
     aracı
    0.06
    **(
    0.06
     stronghold
    0.06
     Stir
    0.06
     coorden
    0.06
    ्तम
    0.05
     providing
    0.05
    emplace
    0.05
    Activations Density 0.003%

    No Known Activations