© 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. 12280
    Prev
    Next
    INDEX
    Explanations

    coding questions

    np_max-act · gemini-2.0-flash

    The neuron fires on common sentence-starting words (like “In,” “It,” “This,” “However,” etc.), effectively detecting the beginnings of sentences or paragraphs.

    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
     kola
    -0.07
    entimes
    -0.06
    ุล
    -0.06
     nota
    -0.06
    觉得
    -0.06
    _SUP
    -0.06
    ，最
    -0.06
    患
    -0.06
    ยาน
    -0.06
    .ON
    -0.06
    POSITIVE LOGITS
     The
    0.07
     the
    0.06
    Crystal
    0.06
     náro
    0.06
    \Catalog
    0.06
     disconnected
    0.06
    vern
    0.06
     giám
    0.06
    k
    0.06
    terms
    0.06
    Activations Density 0.161%

    No Known Activations