© 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. 30461
    Prev
    Next
    INDEX
    Explanations

    her

    np_max-act · gemini-2.0-flash

    This neuron detects the possessive pronoun “her” (as in “his/her”).

    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
     prints
    -0.07
     Packing
    -0.07
     brewing
    -0.07
    Lov
    -0.07
     Fiction
    -0.07
    amt
    -0.06
    215
    -0.06
    ιος
    -0.06
    Last
    -0.06
    Lot
    -0.06
    POSITIVE LOGITS
     SHALL
    0.07
    .setHorizontal
    0.07
     -----------------------------------------------------------------------------↵
    0.07
     누구
    0.07
    /her
    0.07
    แหล
    0.06
     Người
    0.06
    ?↵↵↵
    0.06
     kvinnor
    0.06
    .form
    0.06
    Activations Density 0.004%

    No Known Activations