© 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. 128518
    Prev
    Next
    INDEX
    Explanations

    iveness

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of cost-effectiveness terminology—words and phrases related to economic evaluation (e.g., “cost,” “effectiveness,” “cost‐effectiveness,” “incremental,” “ratio,” “per life year,” “QALY”).

    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
     critique
    -0.06
    ุ์
    -0.06
    	con
    -0.06
    湿
    -0.06
     infer
    -0.06
    .predict
    -0.06
    _CP
    -0.06
     framerate
    -0.05
     hoof
    -0.05
    \Extension
    -0.05
    POSITIVE LOGITS
    urlencode
    0.07
    enin
    0.07
    ایل
    0.07
     WHEN
    0.07
     perhaps
    0.06
    ixo
    0.06
    IBOutlet
    0.06
     відпов
    0.06
     resultList
    0.06
    ồm
    0.06
    Activations Density 0.003%

    No Known Activations