© 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 EvalsExportsinterp-engineNEWAPI 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. 58406
    Prev
    Next
    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash

    The neuron consistently responds to first-person plural references (e.g. “our,” “we”) indicating it detects instances of first-person plural pronouns or possessives.

    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
    Mbps
    -0.07
    CanBe
    -0.06
    930
    -0.06
    extField
    -0.06
    Tai
    -0.06
     přep
    -0.06
    090
    -0.06
    имо
    -0.05
    InParameter
    -0.05
    labilir
    -0.05
    POSITIVE LOGITS
     zwe
    0.08
    차
    0.07
     gesch
    0.07
     &(
    0.06
     phá
    0.06
    .getConfig
    0.06
    PixelFormat
    0.06
    @implementation
    0.06
     I
    0.06
    $i
    0.06
    Activations Density 0.082%

    No Known Activations