© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 102044
    Prev
    Next
    INDEX
    Explanations

    document

    np_max-act · gemini-2.0-flash

    The neuron specifically fires on the “Document” tokens (and adjacent reference numbers) in patent‐citation listings.

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

    technical terminology related to semiconductor devices and manufacturing processes.

    oai_token-act-pair · gpt-4o-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
    OL
    -0.06
     rejected
    -0.06
     laboratories
    -0.06
     replication
    -0.06
     thrilling
    -0.06
     Weiner
    -0.06
     sales
    -0.06
     Presbyterian
    -0.06
    'M
    -0.06
     california
    -0.06
    POSITIVE LOGITS
    ened
    0.07
    genre
    0.07
    �에
    0.06
    _boxes
    0.06
     виду
    0.06
    Body
    0.06
    olet
    0.06
     Rag
    0.06
     lå
    0.06
     직접
    0.06
    Activations Density 0.001%

    No Known Activations