© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109356
    Prev
    Next
    INDEX
    Explanations

    diaper

    np_max-act · gemini-2.0-flash

    The neuron detects references to diapers or diapering (e.g., “nappy,” “diaper,” “pull-ups”) and thus flags baby/infant diaper-related terms.

    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
     salesman
    -0.08
    quire
    -0.07
    .neg
    -0.07
    Evaluate
    -0.07
     nuclei
    -0.07
     Alan
    -0.06
    tele
    -0.06
     Store
    -0.06
    *out
    -0.06
    ınd
    -0.06
    POSITIVE LOGITS
     diaper
    0.11
     diapers
    0.11
    Impro
    0.06
     Orient
    0.06
    роп
    0.06
     jersey
    0.06
     grat
    0.06
     helping
    0.06
     needed
    0.06
    PY
    0.06
    Activations Density 0.002%

    No Known Activations