© 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 EvalsExportsinterp-engineNEWAPI 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. 57592
    Prev
    Next
    INDEX
    Explanations

    Questions and answers

    np_max-act · gemini-2.0-flash

    This neuron detects the assistant’s standard greeting/offering-assistance phrase (e.g. “How can I assist you today?”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    greetings and inquiries for assistance.

    oai_token-act-pair · gpt-4o-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
    	bool
    -0.07
    bx
    -0.07
     Committee
    -0.07
     behaviour
    -0.07
     ******************************************************************************/↵↵
    -0.06
    _STAR
    -0.06
     Meredith
    -0.06
    gd
    -0.06
    kok
    -0.06
    casting
    -0.06
    POSITIVE LOGITS
    #undef
    0.07
    :http
    0.07
     سب
    0.06
    ，都
    0.06
    _dept
    0.06
    .alt
    0.06
     nasıl
    0.06
     "::
    0.06
     Teil
    0.06
     اک
    0.06
    Activations Density 0.029%

    No Known Activations