© 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. 89346
    Prev
    Next
    INDEX
    Explanations

    least

    np_max-act · gemini-2.0-flash

    employee frustrations regarding job satisfaction and efficiency.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on numeric tokens—especially floating-point numbers.

    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
    Gar
    -0.06
     Shir
    -0.06
    Book
    -0.06
    Terr
    -0.06
     Dam
    -0.06
    asio
    -0.06
    Rus
    -0.06
    CTL
    -0.06
    (re
    -0.06
     Sicher
    -0.06
    POSITIVE LOGITS
     fled
    0.07
    )↵
    0.07
     least
    0.07
    .follow
    0.07
     Theo
    0.07
    }))↵
    0.07
     tid
    0.06
     AsyncTask
    0.06
    ,vector
    0.06
     pals
    0.06
    Activations Density 0.008%

    No Known Activations