© 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. 6521
    Prev
    Next
    INDEX
    Explanations

    Quotes and reported speech

    np_max-act · gemini-2.0-flash

    The neuron flags bits of direct speech or quoted dialogue, activating on quotation marks and dialogue markers like “said,” “asked,” and question punctuation.

    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
    .B
    -0.07
    	 ↵
    -0.06
    ccount
    -0.06
     suggestion
    -0.06
     Fantasy
    -0.06
     mit
    -0.06
     Overlay
    -0.06
    .Video
    -0.06
     internet
    -0.06
     wander
    -0.06
    POSITIVE LOGITS
     Toolbox
    0.08
     대한민국
    0.07
    �
    0.07
    柱
    0.06
     cartesian
    0.06
    urgeon
    0.06
    CallCheck
    0.06
     erh
    0.06
     مقدار
    0.06
    化学
    0.06
    Activations Density 0.049%

    No Known Activations