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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 91266
    Prev
    Next
    INDEX
    Explanations

    includes

    np_max-act · gemini-2.0-flash

    This neuron recognizes formal patent‐claim language, especially method steps introduced by “comprising.”

    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
     SE
    -0.07
    No
    -0.06
    their
    -0.06
     AF
    -0.06
     ZIP
    -0.06
     INIT
    -0.06
    (br
    -0.06
    (Resources
    -0.06
    Justice
    -0.06
    งของ
    -0.06
    POSITIVE LOGITS
     anecd
    0.07
    产业
    0.07
    orThunk
    0.06
    �
    0.06
     coi
    0.06
    ได
    0.06
    ؤول
    0.06
     rfl
    0.06
    _utf
    0.06
     ساخته
    0.06
    Activations Density 0.007%

    No Known Activations