© 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. 13418
    Prev
    Next
    INDEX
    Explanations

    conversational writing

    np_max-act · gemini-2.0-flash

    This neuron detects possessive constructions, i.e. words containing an apostrophe to mark ownership (like “people’s,” “others’,” etc.).

    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
    _null
    -0.07
    sembler
    -0.07
     TObject
    -0.07
    र
    -0.06
    Extra
    -0.06
    DbContext
    -0.06
     Rip
    -0.06
    IsActive
    -0.06
    +-+-
    -0.06
     pundits
    -0.06
    POSITIVE LOGITS
    _search
    0.07
    .spring
    0.07
    kre
    0.07
    INUX
    0.06
    orges
    0.06
    agn
    0.06
     langs
    0.06
     तल
    0.06
     mountain
    0.06
    EGA
    0.06
    Activations Density 0.038%

    No Known Activations