© 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. 12753
    Prev
    Next
    INDEX
    Explanations

    g

    np_max-act · gemini-2.0-flash

    The neuron is detecting mentions of caregiving—i.e. occurrences of the word “caregiver” or “caregiving.”

    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
     wre
    -0.07
     United
    -0.06
    εις
    -0.06
    Allocator
    -0.06
     Rwanda
    -0.06
     Uttar
    -0.06
    χα
    -0.06
    工業
    -0.06
     vot
    -0.06
    pants
    -0.06
    POSITIVE LOGITS
    ask
    0.09
     Teachers
    0.07
     Catalyst
    0.06
     VOC
    0.06
    "))))↵
    0.06
     Çev
    0.06
    ainties
    0.06
     vieille
    0.06
     caregivers
    0.06
     caregiver
    0.06
    Activations Density 0.006%

    No Known Activations