© 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. 44141
    Prev
    Next
    INDEX
    Explanations

    XML code

    np_max-act · gemini-2.0-flash

    This neuron detects XML/ XAML attribute names (e.g. the “Class”, “using”, and namespace‐declaration keys) in tag start elements.

    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
    }",
    -0.08
    .us
    -0.07
    ché
    -0.07
     ně
    -0.07
    files
    -0.07
    }`).
    -0.07
    ]],
    -0.06
     soutě
    -0.06
    版
    -0.06
     bitten
    -0.06
    POSITIVE LOGITS
    ackages
    0.07
    background
    0.07
    ehicle
    0.06
     impactful
    0.06
     Его
    0.06
    Rights
    0.06
     Devlet
    0.06
     Coğraf
    0.06
     Honour
    0.06
    ivot
    0.06
    Activations Density 0.031%

    No Known Activations