Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109983
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash

    The neuron primarily detects possessive terms—especially the word "their" (and related ownership markers like "own").

    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
    رياض
    -0.07
    ildenafil
    -0.06
     ample
    -0.06
    arbonate
    -0.06
    -box
    -0.06
     gum
    -0.06
     gé
    -0.06
     Caribbean
    -0.06
    �
    -0.06
    opathic
    -0.06
    POSITIVE LOGITS
    Their
    0.07
     its
    0.07
    ψη
    0.07
     their
    0.06
    ились
    0.06
    ccess
    0.06
    ?’
    0.06
    )c
    0.06
    =((
    0.06
     RTWF
    0.06
    Activations Density 0.010%

    No Known Activations