© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30037
    Prev
    Next
    INDEX
    Explanations

    distributed

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on mentions of “distributed” (and related context words like network, computer, reliable, available), i.e. references to distributed computing systems or architectures.

    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
    Counter
    -0.07
     carbonate
    -0.06
     crossings
    -0.06
     feathers
    -0.06
    anium
    -0.06
     Constructor
    -0.06
    微软雅黑
    -0.06
    ena
    -0.06
    港
    -0.06
    險
    -0.06
    POSITIVE LOGITS
    rgba
    0.07
     distributed
    0.07
    ">@
    0.07
     betr
    0.07
     vern
    0.07
    ณะ
    0.07
     wearable
    0.07
     purs
    0.06
     rooftop
    0.06
     ortadan
    0.06
    Activations Density 0.007%

    No Known Activations