© 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. 41688
    Prev
    Next
    INDEX
    Explanations

    karma

    np_max-act · gemini-2.0-flash

    This neuron fires on occurrences of the word “karma” (as seen in various casing and contexts).

    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
     Educational
    -0.07
    RAR
    -0.07
    	class
    -0.07
     slept
    -0.07
     Serena
    -0.07
     数据
    -0.07
     pinned
    -0.07
    attles
    -0.07
    围
    -0.06
     Riyadh
    -0.06
    POSITIVE LOGITS
     captions
    0.07
     outcome
    0.07
    ْع
    0.06
     cube
    0.06
    oster
    0.06
     serr
    0.06
    _MESSAGES
    0.06
     advancing
    0.06
    .MESSAGE
    0.06
     expands
    0.06
    Activations Density 0.014%

    No Known Activations