© 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. 41310
    Prev
    Next
    INDEX
    Explanations

    concerning/regarding

    np_max-act · gemini-2.0-flash

    The neuron specifically detects formal prepositional discourse markers (e.g. “concerning,” “regarding”) used to introduce or frame a topic in academic or abstract text.

    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
    >Your
    -0.08
     Transform
    -0.07
     antioxidants
    -0.07
     Arts
    -0.07
     Charl
    -0.07
     putchar
    -0.07
    Print
    -0.07
    트
    -0.07
    17
    -0.06
    .StringUtils
    -0.06
    POSITIVE LOGITS
     regarding
    0.12
     concerning
    0.11
    gger
    0.07
     involving
    0.07
    orning
    0.07
    range
    0.07
     covering
    0.07
    gens
    0.07
     fringe
    0.07
    ens
    0.07
    Activations Density 0.019%

    No Known Activations