© 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. 29674
    Prev
    Next
    INDEX
    Explanations

    chain of events

    np_max-act · gemini-2.0-flash

    This neuron responds to temporal/discourse adverbs that indicate sequence (e.g., “then,” “afterwards,” etc.).

    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
    matplotlib
    -0.07
     pochop
    -0.07
    ↵	
    ↵
    -0.06
    scala
    -0.06
     });
    ↵
    ↵
    -0.06
    inis
    -0.06
    ↵ ↵
    -0.06
    _dropout
    -0.06
    /
    ↵
    ↵
    -0.06
     {
    ↵
    ↵
    ↵
    -0.06
    POSITIVE LOGITS
    (all
    0.07
     Hello
    0.06
     congregation
    0.06
    =DB
    0.06
     بو
    0.06
    InThe
    0.06
     exploded
    0.06
     monster
    0.06
    Este
    0.06
     plate
    0.06
    Activations Density 0.045%

    No Known Activations