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. 84988
    Prev
    Next
    INDEX
    Explanations

    generally

    np_max-act · gemini-2.0-flash

    This neuron detects the patent-style “Field of the Invention” phrasing, in particular the “the present invention relates generally to” construction.

    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
     Checklist
    -0.07
     Seeking
    -0.07
    	operator
    -0.06
    Prices
    -0.06
     Mir
    -0.06
    icated
    -0.06
    cod
    -0.06
     healthcare
    -0.06
    aat
    -0.06
    Run
    -0.06
    POSITIVE LOGITS
     ανά
    0.07
    multiline
    0.07
     HomeComponent
    0.06
    няття
    0.06
    алося
    0.06
    usher
    0.06
     analý
    0.06
     sts
    0.06
    _Q
    0.06
     novelty
    0.06
    Activations Density 0.002%

    No Known Activations