© 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. 91264
    Prev
    Next
    INDEX
    Explanations

    Assume

    np_max-act · gemini-2.0-flash

    This neuron highlights numeric tokens showing decimal values (e.g., amounts with decimal points).

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

    Instances of section headings, labels, or other document-structure/meta-information (e.g., headers like "The following", "About myself", "Here are", field names).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    Document
    -0.07
    skirts
    -0.06
     mercy
    -0.06
    uds
    -0.06
    UD
    -0.06
     chefs
    -0.06
    ils
    -0.06
    Sale
    -0.06
    ूह
    -0.06
     compilers
    -0.06
    POSITIVE LOGITS
    "",
    0.08
     desarroll
    0.07
     yytype
    0.06
    .getLocal
    0.06
    ',{'
    0.06
    .stack
    0.06
     Institutions
    0.06
    _GT
    0.06
    .Unicode
    0.06
    -non
    0.06
    Activations Density 0.700%

    No Known Activations