© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 17925
    Prev
    Next
    INDEX
    Explanations

    t

    np_max-act · gemini-2.0-flash

    terms related to specific medical or health conditions and their treatments.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on domain-specific jargon—specialized technical or system names, chemical and medical terms, identifiers, etc.—rather than ordinary words.

    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
    ddit
    -0.07
    ючись
    -0.07
    enario
    -0.07
    .properties
    -0.07
    .Build
    -0.07
    utto
    -0.06
     tenure
    -0.06
     annual
    -0.06
    nav
    -0.06
     spirits
    -0.06
    POSITIVE LOGITS
    apgolly
    0.07
     meetup
    0.07
    tent
    0.07
     ajout
    0.06
     HAR
    0.06
    *"
    0.06
    Cx
    0.06
     Farage
    0.06
     öngör
    0.06
     tä
    0.06
    Activations Density 0.341%

    No Known Activations