© 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. 38440
    Prev
    Next
    INDEX
    Explanations

    California energy market

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect tokens related to energy and electricity markets (e.g. “power,” “electricity,” “California,” “market,” “crisis,” “prices,” “deregulation,” etc.).

    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
    .getOwnPropertyDescriptor
    -0.07
     imkân
    -0.07
    icits
    -0.06
     contradict
    -0.06
     PASSWORD
    -0.06
     Stella
    -0.06
     Arcade
    -0.06
    LEncoder
    -0.06
     İmpar
    -0.06
    cordova
    -0.06
    POSITIVE LOGITS
    ','.
    0.08
     ras
    0.07
    /com
    0.07
     ris
    0.07
    atisfied
    0.06
     fertilizer
    0.06
    .arrow
    0.06
    _COM
    0.06
     Fem
    0.06
     signed
    0.06
    Activations Density 0.014%

    No Known Activations