© 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. 126298
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns in stories

    np_max-act · gemini-2.0-flash

    The neuron primarily detects third-person possessive pronouns (e.g. his, her, their).

    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
    	len
    -0.07
     cunning
    -0.07
    typeof
    -0.06
     Worth
    -0.06
     wnd
    -0.06
    .refresh
    -0.06
     NW
    -0.06
    -kind
    -0.06
     Kun
    -0.06
    algorithm
    -0.06
    POSITIVE LOGITS
     chung
    0.07
    /DTD
    0.06
    .language
    0.06
    吸
    0.06
    ?>>↵
    0.06
    ソ
    0.06
    chron
    0.06
     frowned
    0.06
    biased
    0.06
     yours
    0.06
    Activations Density 0.038%

    No Known Activations