© 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. 30517
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash

    This neuron primarily activates on the plural possessive pronoun “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
    zon
    -0.07
    hasMany
    -0.07
     CREATED
    -0.06
    -notes
    -0.06
    “When
    -0.06
    اپیم
    -0.06
    [OF
    -0.06
     помощи
    -0.06
    _worker
    -0.06
     своими
    -0.06
    POSITIVE LOGITS
     coherence
    0.06
     White
    0.06
     member
    0.06
     дв
    0.06
    liquid
    0.06
     oltre
    0.06
     stricter
    0.06
     Collect
    0.06
     assertThat
    0.06
     환경
    0.06
    Activations Density 0.020%

    No Known Activations