© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30581
    Prev
    Next
    INDEX
    Explanations

    invention

    np_max-act · gemini-2.0-flash

    The neuron selectively fires on the word “invention” (and its immediate boilerplate context) marking the patent’s introductory “This invention …” phrasing.

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

    technical descriptions of inventions related to advanced materials and engineering processes.

    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
    Compare
    -0.07
    RowIndex
    -0.07
     качестве
    -0.07
     Calories
    -0.07
    List
    -0.07
     winds
    -0.06
    ool
    -0.06
    _VIS
    -0.06
    [ip
    -0.06
    Dropdown
    -0.06
    POSITIVE LOGITS
     Прод
    0.06
     берез
    0.06
     самый
    0.06
    isd
    0.06
    buyer
    0.06
    .BASELINE
    0.06
     Auditor
    0.06
    .Serializer
    0.06
     """
↵
↵
    0.06
     تون
    0.06
    Activations Density 0.003%

    No Known Activations