© 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. 126410
    Prev
    Next
    INDEX
    Explanations

    cumbersome

    np_max-act · gemini-2.0-flash

    The neuron flags negative descriptive adjectives that characterize something as cumbersome, awkward, or otherwise inconvenient.

    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
    应该
    -0.07
    実
    -0.07
    Empleado
    -0.07
    .am
    -0.06
    	Date
    -0.06
    init
    -0.06
    ับ
    -0.06
     north
    -0.06
    INIT
    -0.06
     organise
    -0.06
    POSITIVE LOGITS
     cumbersome
    0.10
     awkward
    0.07
     Paulo
    0.07
     fashioned
    0.07
     cramped
    0.07
     datové
    0.07
    pixels
    0.07
     Osman
    0.07
     Polish
    0.07
     clumsy
    0.06
    Activations Density 0.009%

    No Known Activations