© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44426
    Prev
    Next
    INDEX
    Explanations

    donations

    np_max-act · gemini-2.0-flash

    This neuron responds to language about community support and charity—mentions of donations, generosity, and expressions of thanks.

    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
    	retval
    -0.07
     Alpha
    -0.06
    амп
    -0.06
    	tc
    -0.06
    degree
    -0.06
     saturn
    -0.06
    Hour
    -0.06
    Pane
    -0.06
     ăn
    -0.06
     Desktop
    -0.06
    POSITIVE LOGITS
    .contentMode
    0.07
    :end
    0.07
    .`);↵
    0.07
     pulmonary
    0.07
    !!");↵
    0.07
    (())↵
    0.07
     initWithFrame
    0.06
     لل
    0.06
     الخامسة
    0.06
    ]initWithFrame
    0.06
    Activations Density 0.069%

    No Known Activations