© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43308
    Prev
    Next
    INDEX
    Explanations

    speaker

    np_max-act · gemini-2.0-flash

    This neuron responds to deeply emotional, affectionate language—expressions of love, gratitude, and intimate caring.

    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
     вполне
    -0.06
     найд
    -0.06
     پل
    -0.06
    			
    ↵
    -0.06
     fullPath
    -0.06
     physiological
    -0.06
     August
    -0.06
    avra
    -0.06
     Exists
    -0.06
     春
    -0.05
    POSITIVE LOGITS
    .getBoundingClientRect
    0.07
     ajax
    0.06
    .sn
    0.06
    maze
    0.06
    upiter
    0.06
    	cm
    0.06
    ửi
    0.06
    	queue
    0.06
     작
    0.06
    floor
    0.06
    Activations Density 0.029%

    No Known Activations