© 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
    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. 91532
    Prev
    Next
    INDEX
    Explanations

    scientific facilities

    np_max-act · gemini-2.0-flash

    The neuron fires on names and mentions of big‐science user facilities—especially synchrotron and neutron sources, beamlines, X-ray stations, and their associated identifiers.

    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
     gerekir
    -0.07
    apers
    -0.06
     clips
    -0.06
     erosion
    -0.06
    shape
    -0.06
    ीदव
    -0.06
    ạng
    -0.06
    бина
    -0.06
     slide
    -0.06
     helps
    -0.05
    POSITIVE LOGITS
    .weixin
    0.07
     pequ
    0.07
    :true
    0.07
    real
    0.07
    uento
    0.07
    iểu
    0.07
    izacao
    0.07
    ayette
    0.06
    ened
    0.06
    .flags
    0.06
    Activations Density 0.012%

    No Known Activations