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. 40392
    Prev
    Next
    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash

    legal terms and references.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on capitalized name fragments—i.e. it detects personal proper names (especially attorneys’ or parties’ surnames) in the legal document.

    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
     pond
    -0.07
     Clint
    -0.06
    -plus
    -0.06
    Phone
    -0.06
     Opr
    -0.06
    ्पन
    -0.06
    oubtedly
    -0.06
     spac
    -0.06
    小姐
    -0.06
     služeb
    -0.06
    POSITIVE LOGITS
     popul
    0.07
    ลล
    0.07
    requently
    0.06
    ()
    ↵
    ↵
    ↵
    0.06
    문제
    0.06
    骑
    0.06
    odynamics
    0.06
    ?↵↵↵↵
    0.06
    modification
    0.06
     âm
    0.06
    Activations Density 0.022%

    No Known Activations