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

    Neuronpedia

    Jacobian LensNEW
    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. 56845
    Prev
    Next
    INDEX
    Explanations

    following, attached

    np_max-act · gemini-2.0-flash

    This neuron detects the stock phrase introducing a draft—specifically the “following draft with” part at the start of assistant responses.

    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
     Temple
    -0.07
    irk
    -0.07
     refill
    -0.06
     bold
    -0.06
     серед
    -0.06
    _Buffer
    -0.06
     selecting
    -0.06
    ntag
    -0.06
     Пол
    -0.06
     G
    -0.06
    POSITIVE LOGITS
     excl
    0.07
    _NV
    0.06
    pendicular
    0.06
    /alert
    0.06
     معل
    0.06
     duvar
    0.06
     hấp
    0.06
    adora
    0.06
     prosperous
    0.06
     apro
    0.06
    Activations Density 0.002%

    No Known Activations