© 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. 126923
    Prev
    Next
    INDEX
    Explanations

    complex

    np_max-act · gemini-2.0-flash

    The neuron fires on mention of chemical coordination “complexes” (and related descriptors like Complex, dinuclear, trivalent, octahedral, etc.) in scientific text.

    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
     ape
    -0.06
    odied
    -0.06
    (sheet
    -0.06
     SON
    -0.06
     BITS
    -0.06
     му
    -0.06
    _lvl
    -0.06
    ableObject
    -0.06
    بد
    -0.06
    皮
    -0.06
    POSITIVE LOGITS
     Soldier
    0.08
     следующие
    0.07
     Prior
    0.07
     surrender
    0.07
     많은
    0.06
                                                                     
    0.06
     pilot
    0.06
    .F
    0.06
    ประม
    0.06
     specialists
    0.06
    Activations Density 0.012%

    No Known Activations