© 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. 42510
    Prev
    Next
    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash

    This neuron detects tokens that mark or connect items in an enumerated list—words like “any,” commas, and “or.”

    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
    PDO
    -0.07
     GtkWidget
    -0.07
     خیابان
    -0.06
    ेर
    -0.06
     حوزه
    -0.06
    _Common
    -0.06
    wrapped
    -0.06
     Silicon
    -0.06
    (properties
    -0.06
    Iraq
    -0.06
    POSITIVE LOGITS
    _iff
    0.07
    /meta
    0.07
    	side
    0.06
     ┃
    0.06
    	manager
    0.06
     gs
    0.06
     Dwarf
    0.06
     Мож
    0.06
     jaz
    0.06
    (cube
    0.06
    Activations Density 0.009%

    No Known Activations