© 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. 54179
    Prev
    Next
    INDEX
    Explanations

    Information extraction

    np_max-act · gemini-2.0-flash

    This neuron activates on uppercase NER entity‐type labels (e.g. DATE, FACILITY, ORGANIZATION, PHONE, NUMBERS, PRODUCT) 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
     instincts
    -0.07
    .activity
    -0.06
    lej
    -0.06
     Subscribe
    -0.06
     đế
    -0.06
     castle
    -0.06
    ienne
    -0.06
    theast
    -0.06
     Offline
    -0.06
    _^
    -0.06
    POSITIVE LOGITS
    vertex
    0.07
    userName
    0.06
    _send
    0.06
    implicitly
    0.06
    Proceed
    0.06
    σύ
    0.06
    _allocation
    0.06
     Rout
    0.06
    '),
↵
    0.06
    ******↵↵
    0.06
    Activations Density 0.007%

    No Known Activations