© 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. 108967
    Prev
    Next
    INDEX
    Explanations

    scientific materials and methods

    np_max-act · gemini-2.0-flash

    This neuron detects section-heading tokens, especially the “METHODS” (and related numbering/formatting) labels in the document.

    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
     Maher
    -0.07
     Зах
    -0.07
    Un
    -0.07
    ..
    -0.07
    ентами
    -0.06
    ;
↵
↵
↵
↵
    -0.06
    Micro
    -0.06
     Weekend
    -0.06
     clearing
    -0.06
    Wildcard
    -0.06
    POSITIVE LOGITS
    ليزية
    0.07
     didFinish
    0.06
    _buffers
    0.06
    _session
    0.06
     cocktail
    0.06
     адрес
    0.06
    άνει
    0.06
    透
    0.06
     Mississippi
    0.06
    цеп
    0.06
    Activations Density 0.004%

    No Known Activations