© 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. 8829
    Prev
    Next
    INDEX
    Explanations

    email addresses

    np_max-act · gemini-2.0-flash

    The neuron activates on parts of email addresses (the “E-mail:” label, the “@” sign, and the surrounding username/host tokens).

    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
    .called
    -0.08
    reeNode
    -0.07
    END
    -0.07
    FEATURE
    -0.06
     nied
    -0.06
    \Log
    -0.06
    /object
    -0.06
     jig
    -0.06
    ria
    -0.06
    .Search
    -0.06
    POSITIVE LOGITS
     ])↵
    0.08
    -relative
    0.08
     Elk
    0.07
    _it
    0.06
     WhatsApp
    0.06
     NOTIFY
    0.06
     sticks
    0.06
    _SUITE
    0.06
     leggings
    0.06
    르게
    0.06
    Activations Density 0.046%

    No Known Activations