© 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. 110711
    Prev
    Next
    INDEX
    Explanations

    genes and proteins

    np_max-act · gemini-2.0-flash

    This neuron activates on technical terms referring to molecular‐biology profiling and measurement—especially words like “protein,” “expression,” “gene,” “proteomic,” and “analysis.”

    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
    >Error
    -0.07
    EA
    -0.07
     sene
    -0.07
     carga
    -0.06
     advertise
    -0.06
    _YUV
    -0.06
     tokenizer
    -0.06
    equalTo
    -0.06
    ณ
    -0.06
    ol
    -0.06
    POSITIVE LOGITS
    600
    0.06
    知
    0.06
    육
    0.06
    997
    0.06
     쉬
    0.06
     مت
    0.06
    ні
    0.06
     Vogue
    0.06
    이었
    0.06
     inflamm
    0.06
    Activations Density 0.050%

    No Known Activations