© 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. 7890
    Prev
    Next
    INDEX
    Explanations

    hobbies and instrument playing

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the second-person pronoun “you” (and variants like “you’ll,” “you may,” “you can”) in assistant output.

    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
     ################################
    -0.06
     MPC
    -0.06
     hostname
    -0.06
    avatel
    -0.06
    าณ
    -0.06
     propane
    -0.06
    vt
    -0.06
    _weight
    -0.06
     legalize
    -0.06
     solder
    -0.06
    POSITIVE LOGITS
     Club
    0.07
    �
    0.07
    ItemSelected
    0.07
     польз
    0.07
    _Order
    0.07
     playerId
    0.06
    uby
    0.06
    λού
    0.06
     CLUB
    0.06
    UserId
    0.06
    Activations Density 0.070%

    No Known Activations