© 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. 29901
    Prev
    Next
    INDEX
    Explanations

    patents

    np_max-act · gemini-2.0-flash

    The neuron detects numeric identifiers—especially patent/application serial numbers and other multi‐part digit strings with decimals.

    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
     данных
    -0.06
     distressed
    -0.06
     replied
    -0.06
    弋
    -0.06
    .ReadFile
    -0.06
     použití
    -0.06
     ---
    -0.06
    爸
    -0.06
    genesis
    -0.06
    _guide
    -0.06
    POSITIVE LOGITS
    $num
    0.08
    -command
    0.07
     No
    0.07
     Baby
    0.06
    üne
    0.06
     مه
    0.06
     accommodations
    0.06
     assistants
    0.06
     전세가
    0.06
     Schwarz
    0.06
    Activations Density 0.003%

    No Known Activations