© 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. 108814
    Prev
    Next
    INDEX
    Explanations

    Academic essays

    np_max-act · gemini-2.0-flash

    This neuron lights up on words that appear in section or document titles and headings—typically capitalized content words at the start of titles.

    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
     diamonds
    -0.07
     remedy
    -0.06
     Morocco
    -0.06
     creamy
    -0.06
    vý
    -0.06
    飛
    -0.06
    (dc
    -0.06
    ất
    -0.06
     activates
    -0.06
     edges
    -0.06
    POSITIVE LOGITS
    їв
    0.06
     увид
    0.06
     Hamas
    0.06
     XElement
    0.06
    =root
    0.06
    puties
    0.06
    _Tag
    0.06
     sometime
    0.06
    	th
    0.06
     γυνα
    0.06
    Activations Density 0.117%

    No Known Activations