© 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
    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. 110555
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron activates on temporal/conditional markers introducing events (e.g. “When,” “Once,” “triggered,” “actuated,” “applied”) that set up “when X happens, then Y” clauses.

    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
    icer
    -0.07
    .enumer
    -0.07
     engagements
    -0.06
    "--
    -0.06
     gridColumn
    -0.06
    _refs
    -0.06
    ��
    -0.06
    /Edit
    -0.06
     로
    -0.06
    .false
    -0.06
    POSITIVE LOGITS
     undergo
    0.07
    (calendar
    0.06
    ,min
    0.06
     bất
    0.06
    bstract
    0.06
     Osw
    0.06
    ص
    0.06
       ↵
    0.06
    deque
    0.06
    :uint
    0.06
    Activations Density 0.046%

    No Known Activations