© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 58685
    Prev
    Next
    INDEX
    Explanations

    music

    np_max-act · gemini-2.0-flash

    The neuron mainly detects numerical tokens, especially years and decade references.

    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
    659
    -0.07
    616
    -0.07
    irim
    -0.07
     thừa
    -0.07
    isions
    -0.06
     список
    -0.06
     antennas
    -0.06
     YE
    -0.06
    	handle
    -0.06
    }</
    -0.06
    POSITIVE LOGITS
    _popup
    0.07
     External
    0.06
     बर
    0.06
     "[%
    0.06
     decom
    0.06
     labelText
    0.06
    ////////////////////////////////////////////////////////////////////////////////////////////////
    0.06
     Перв
    0.06
    \db
    0.06
     респ
    0.06
    Activations Density 0.021%

    No Known Activations