© 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. 29650
    Prev
    Next
    INDEX
    Explanations

    complex

    np_max-act · gemini-2.0-flash

    This neuron primarily activates on occurrences of the word “complex.”

    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
     Rit
    -0.07
     rif
    -0.07
     tat
    -0.07
    utton
    -0.07
    tir
    -0.07
    attrib
    -0.07
     Robinson
    -0.07
    dar
    -0.07
     tt
    -0.07
     runners
    -0.07
    POSITIVE LOGITS
     complex
    0.12
     Complex
    0.12
     complexes
    0.10
    complex
    0.10
    Complex
    0.09
     Cross
    0.09
     complexion
    0.08
     Deluxe
    0.08
    Alex
    0.08
    (mx
    0.08
    Activations Density 0.026%

    No Known Activations