© 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. 38162
    Prev
    Next
    INDEX
    Explanations

    Internet forum texts

    np_max-act · gemini-2.0-flash

    The neuron fires on words framing an expectation of others doing something for you (e.g. “to,” “do,” “favors,” “for you,” “expecting”). It flags entitlement/asking‐favors contexts.

    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
     Hills
    -0.07
    dispatcher
    -0.07
    =search
    -0.07
     століття
    -0.07
     accessibility
    -0.06
    bk
    -0.06
     zase
    -0.06
     CAP
    -0.06
    .creator
    -0.06
    ivot
    -0.06
    POSITIVE LOGITS
    oplevel
    0.07
    []):
    0.07
     polygons
    0.06
     ElementRef
    0.06
     GLfloat
    0.06
     Lond
    0.06
     OMG
    0.06
    (/\
    0.06
    (',',$
    0.06
    autoload
    0.06
    Activations Density 0.004%

    No Known Activations