© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 37969
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash

    The neuron specifically fires on the noun (or noun‐like word) that follows an initial “In [pronoun]” phrase (e.g. In his short life, In my estimation, In her defence).

    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
    ,the
    -0.07
     divid
    -0.07
     The
    -0.07
    667
    -0.07
    行业
    -0.06
    The
    -0.06
    技能
    -0.06
     List
    -0.06
     دو
    -0.06
     roster
    -0.06
    POSITIVE LOGITS
    管
    0.08
     @[
    0.07
     profesyonel
    0.06
     my
    0.06
    。我
    0.06
     Our
    0.06
    adians
    0.06
     手
    0.06
     OnCollision
    0.06
     Wir
    0.06
    Activations Density 0.029%

    No Known Activations