© 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 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. 38504
    Prev
    Next
    INDEX
    Explanations

    Mobile applications

    np_max-act · gemini-2.0-flash

    The neuron activates on list‐item markers (numbered bullets like “1.”, “2.”, “*”, etc.), i.e. tokens that indicate enumeration in the text.

    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
     gadget
    -0.06
    ्रण
    -0.06
    _STRING
    -0.06
     Manip
    -0.06
    while
    -0.06
    atrigesimal
    -0.06
    üyük
    -0.06
    .await
    -0.06
    .consumer
    -0.05
    ideo
    -0.05
    POSITIVE LOGITS
    _rename
    0.07
     tvoří
    0.06
     امور
    0.06
     peril
    0.06
     ',↵
    0.06
     zusammen
    0.06
     creeping
    0.06
     spar
    0.06
     ат
    0.06
    !).↵↵
    0.06
    Activations Density 0.076%

    No Known Activations