© 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. 56266
    Prev
    Next
    INDEX
    Explanations

    oton

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of photon‐based nonlinear optical processes, especially multi‐photon excitation terms (e.g. “two‐photon,” “three‐photon”).

    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
     Cass
    -0.06
     normals
    -0.06
    カテ
    -0.06
     ти
    -0.06
     tanım
    -0.06
     sept
    -0.06
     změny
    -0.06
     исп
    -0.06
     tty
    -0.06
    .dispatcher
    -0.06
    POSITIVE LOGITS
    /$',
    0.07
    訪
    0.07
     Review
    0.07
    768
    0.07
     foreigners
    0.07
     также
    0.06
     Vertical
    0.06
     már
    0.06
     水
    0.06
     Conservatives
    0.06
    Activations Density 0.002%

    No Known Activations