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

    Neuronpedia

    Jacobian LensNEW
    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. 38704
    Prev
    Next
    INDEX
    Explanations

    medical care

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of insurance network scope or coverage areas, i.e. references to “network” and related terms about where services fall inside or outside that network.

    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
     shape
    -0.07
     chicks
    -0.06
    ेव
    -0.06
     owners
    -0.06
     interactions
    -0.06
     tarif
    -0.06
     fib
    -0.06
    .diff
    -0.06
     Georges
    -0.06
    Managed
    -0.06
    POSITIVE LOGITS
     následující
    0.07
     "'.
    0.06
     čís
    0.06
     Kuzey
    0.06
    ��
    0.06
     Burgess
    0.06
    malink
    0.06
    UInteger
    0.06
    )>=
    0.06
    .Minute
    0.06
    Activations Density 0.022%

    No Known Activations