© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 91116
    Prev
    Next
    INDEX
    Explanations

    graph

    np_max-act · gemini-2.0-flash

    The neuron responds to occurrences of Graph API hostnames in URLs (e.g. “graph.facebook.com” or “graph.microsoft.com”).

    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
     helped
    -0.06
     П
    -0.06
    險
    -0.06
     lor
    -0.06
    umas
    -0.06
     hỏi
    -0.06
     Tas
    -0.06
     olacak
    -0.06
    oystick
    -0.06
     vững
    -0.06
    POSITIVE LOGITS
    atural
    0.08
    男性
    0.07
    χία
    0.06
     ApplicationDbContext
    0.06
    (one
    0.06
    $return
    0.06
    >{{$
    0.06
    straight
    0.06
    
    0.06
     feed
    0.06
    Activations Density 0.002%

    No Known Activations