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

    Neuronpedia

    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. 68475
    Prev
    Next
    INDEX
    Explanations

    magazine and news publications

    np_max-act · gemini-2.0-flash

    incidents of crime and violence.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron flags boilerplate “about us” or promotional taglines and mission‐statement blurbs describing publications, brands, or media outlets.

    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
    orta
    -0.07
     construction
    -0.07
     case
    -0.07
    .currentIndex
    -0.07
     collaborators
    -0.07
    NX
    -0.06
     {{↵
    -0.06
     BM
    -0.06
     punch
    -0.06
    อง
    -0.06
    POSITIVE LOGITS
    änge
    0.07
    姑
    0.06
     evento
    0.06
    ibilidad
    0.06
    senha
    0.06
    Documento
    0.06
     захисту
    0.06
    Sibling
    0.06
     applicationWill
    0.06
    .Rec
    0.06
    Activations Density 0.021%

    No Known Activations