© 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
    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. 41358
    Prev
    Next
    INDEX
    Explanations

    detected

    np_max-act · gemini-2.0-flash

    The neuron responds to the log phrase “Variances detected in … schedule,” i.e. it flags the words around “Variances detected in” when a variance is reported in a schedule.

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

    variances detected in energy import/export schedules.

    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
    ivers
    -0.08
    Hair
    -0.06
    Cisco
    -0.06
     metropolitan
    -0.06
    _contrib
    -0.06
     newbie
    -0.06
    ()?
    -0.06
     comprising
    -0.06
     Downs
    -0.06
    ¨¨
    -0.06
    POSITIVE LOGITS
     �
    0.07
    oons
    0.06
    크
    0.06
     swirling
    0.06
     deputies
    0.06
    Salir
    0.06
    qué
    0.06
    리어
    0.06
    ">\
    0.06
     productList
    0.06
    Activations Density 0.176%

    No Known Activations