Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 40550
    Prev
    Next
    INDEX
    Explanations

    paralysis and mobility

    np_max-act · gemini-2.0-flash

    The neuron fires on text describing physical disabilities and mobility impairments—e.g. paralysis, loss of function in limbs, assistive devices, and related medical conditions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    references to disabilities and their impacts on individuals' lives.

    oai_token-act-pair · gpt-4o-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
     결혼
    -0.07
    au
    -0.06
     orc
    -0.06
     María
    -0.06
     LT
    -0.06
    nan
    -0.06
    isters
    -0.06
    гу
    -0.06
     más
    -0.06
     complain
    -0.06
    POSITIVE LOGITS
    _USB
    0.07
     Convenience
    0.07
     nackte
    0.07
     NSCoder
    0.06
    (Object
    0.06
    нар
    0.06
    ("../../
    0.06
    (dynamic
    0.06
    ไทย
    0.06
    .Diagnostics
    0.06
    Activations Density 0.012%

    No Known Activations