© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 92436
    Prev
    Next
    INDEX
    Explanations

    close

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens—especially decimal or floating‐point figures used for stock prices, points, and financial metrics.

    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
    として
    -0.07
     thirteen
    -0.07
    这样的
    -0.07
    กราคม
    -0.06
    3
    -0.06
    ические
    -0.06
     pioneered
    -0.06
     дослідження
    -0.06
    цией
    -0.06
     fur
    -0.06
    POSITIVE LOGITS
    sko
    0.06
     tonnes
    0.06
    ower
    0.06
    bower
    0.06
     Χα
    0.06
     pert
    0.06
    /fa
    0.06
    _poll
    0.06
     báo
    0.06
    .shell
    0.06
    Activations Density 0.006%

    No Known Activations