© 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. 87923
    Prev
    Next
    INDEX
    Explanations

    Internet comments in multiple languages

    np_max-act · gemini-2.0-flash

    This neuron detects rare or out-of-distribution tokens—especially special control markers (e.g. `<|eot_id|>`) and uncommon proper nouns or prefixes.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    references to specific video game items and their functionalities.

    oai_token-act-pair · gpt-4o-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
    One
    -0.07
     Aç
    -0.06
     Iter
    -0.06
    Until
    -0.06
     خبر
    -0.06
    XR
    -0.06
    Distribution
    -0.06
     Barker
    -0.06
     Howe
    -0.06
    UpdateTime
    -0.06
    POSITIVE LOGITS
    )][
    0.07
    .ravel
    0.07
    imedia
    0.06
    .LogInformation
    0.06
    ença
    0.06
    (Binary
    0.06
     irc
    0.06
    ELCOME
    0.06
     placeholder
    0.06
    ‌است
    0.06
    Activations Density 0.047%

    No Known Activations