© 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. 13085
    Prev
    Next
    INDEX
    Explanations

    disposal

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on mentions of disposing of chemical materials, especially instructions and terms around “dispose,” “disposal,” and “waste.”

    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
    eted
    -0.06
     Hend
    -0.06
     nuclei
    -0.06
     languages
    -0.06
    ीग
    -0.06
     ringing
    -0.06
    shot
    -0.06
    _SENSOR
    -0.06
    สถาน
    -0.06
    Synopsis
    -0.06
    POSITIVE LOGITS
     Journal
    0.07
    '>↵↵
    0.07
    Pear
    0.07
     تصمیم
    0.07
    腰
    0.06
    Forms
    0.06
    ()`
    0.06
     آنلاین
    0.06
    ?)↵↵
    0.06
     vfs
    0.06
    Activations Density 0.007%

    No Known Activations