© 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. 56157
    Prev
    Next
    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash

    This neuron detects evaluative legal terms and phrases in a court opinion that express approval or confirmation of prior rulings (e.g. appropriately, implemented, affirmed, rejected).

    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
    ительные
    -0.07
     ----------------------------------------------------------------------------------------------------------------
    -0.06
     mimic
    -0.06
     attacks
    -0.06
    	pre
    -0.06
     Minh
    -0.06
     improbable
    -0.06
    WHERE
    -0.06
    	line
    -0.06
     Typ
    -0.06
    POSITIVE LOGITS
     rightfully
    0.07
    ική
    0.07
    clipboard
    0.07
     comentarios
    0.07
    tributes
    0.06
    .Console
    0.06
     Dias
    0.06
    abled
    0.06
    elfast
    0.06
    ush
    0.06
    Activations Density 0.030%

    No Known Activations