© 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. 89188
    Prev
    Next
    INDEX
    Explanations

    Real estate transactions

    np_max-act · gemini-2.0-flash

    references to real estate transactions and market trends.

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

    The neuron detects mentions of real‐estate transaction events (sales, leases, units sold/leased) often in statistical or numeric contexts.

    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
    へと
    -0.07
     یکی
    -0.06
     ed
    -0.06
     věn
    -0.06
     sıcak
    -0.06
    vu
    -0.06
     evaluated
    -0.06
     uygun
    -0.06
     textView
    -0.06
     predicted
    -0.06
    POSITIVE LOGITS
    -role
    0.07
    με
    0.07
    (mutex
    0.07
    (Initialized
    0.06
    _perms
    0.06
    -bo
    0.06
    \R
    0.06
    (point
    0.06
    ;m
    0.06
    .jquery
    0.06
    Activations Density 0.017%

    No Known Activations