© 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. 6117
    Prev
    Next
    INDEX
    Explanations

    current

    np_max-act · gemini-2.0-flash

    The neuron activates on words referring to up-to-date information or news (e.g. “news,” “current,” “recent,” “events”).

    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
    (OpCodes
    -0.07
    Magn
    -0.07
     maritime
    -0.07
     difficult
    -0.07
     Registry
    -0.06
     Vita
    -0.06
    وقف
    -0.06
     provision
    -0.06
     Zuckerberg
    -0.06
     Rach
    -0.06
    POSITIVE LOGITS
    beit
    0.06
     yelling
    0.06
     FIXED
    0.06
     Alice
    0.06
    quared
    0.06
    aptops
    0.06
    úc
    0.06
    _PUSH
    0.06
    axes
    0.06
    hort
    0.06
    Activations Density 0.010%

    No Known Activations