© 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. 92073
    Prev
    Next
    INDEX
    Explanations

    hear

    np_max-act · gemini-2.0-flash

    conversations indicating social interactions and dynamics among peers.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on expressions of sympathy or apology (e.g., “I’m sorry to hear that”).

    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
    deployment
    -0.07
    Metro
    -0.06
    _protocol
    -0.06
     majestic
    -0.06
    liğini
    -0.06
    VIC
    -0.06
    nest
    -0.06
    naissance
    -0.06
    :block
    -0.06
     utiliza
    -0.06
    POSITIVE LOGITS
     #↵
    0.06
    ै↵
    0.06
                
↵
    0.06
    อากาศ
    0.06
    !")↵
    0.06
        
↵
    0.06
    &↵
    0.06
     strcpy
    0.06
     &,
    0.06
    éc
    0.06
    Activations Density 0.004%

    No Known Activations