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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92574
    Prev
    Next
    INDEX
    Explanations

    Science and health

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of specific technology domains or platforms (e.g. “autonomous driving,” “TensorFlow,” “IoT”).

    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
     extr
    -0.07
     Tibetan
    -0.07
    Cx
    -0.07
     Nan
    -0.06
     designation
    -0.06
     дости
    -0.06
     property
    -0.06
     OK
    -0.06
    Bar
    -0.06
    alat
    -0.06
    POSITIVE LOGITS
     Writes
    0.06
    [idx
    0.06
    nými
    0.06
     usando
    0.06
     Toggle
    0.06
     العن
    0.06
    лася
    0.06
    [j
    0.06
     слух
    0.06
     pll
    0.06
    Activations Density 0.096%

    No Known Activations