© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6990
    Prev
    Next
    INDEX
    Explanations

    .props

    np_max-act · gemini-2.0-flash

    The neuron fires on MSBuild/Visual-Studio XML import lines—especially the “Import Project=...Default.props” elements referring to “.props” files.

    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
     CTL
    -0.07
    atrigesimal
    -0.07
     Möglich
    -0.06
     церк
    -0.06
     cwd
    -0.06
     Brigade
    -0.06
     cavalry
    -0.06
    .AttributeSet
    -0.06
    在线阅读
    -0.06
    Dar
    -0.06
    POSITIVE LOGITS
    .ant
    0.07
    فی
    0.07
    !!↵↵
    0.07
     scrapped
    0.07
     forks
    0.07
    ramework
    0.06
    inos
    0.06
    ']]],↵
    0.06
     theorists
    0.06
     homo
    0.06
    Activations Density 0.001%

    No Known Activations