© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 73799
    Prev
    Next
    INDEX
    Explanations

    S

    np_max-act · gemini-2.0-flash

    The neuron is sensitive to structural or “meta‐text” tokens—things like section titles, headings, standalone numbers, and other document-level markers.

    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
     irm
    -0.07
    conte
    -0.07
    etyl
    -0.07
     tras
    -0.07
     seguir
    -0.07
     Hide
    -0.07
     Cindy
    -0.06
    iena
    -0.06
     plata
    -0.06
     Rot
    -0.06
    POSITIVE LOGITS
     поки
    0.06
     merch
    0.06
     putStrLn
    0.06
    quarters
    0.06
    -в
    0.06
    ==>
    0.06
     Dolphin
    0.06
     see
    0.06
     Dutch
    0.06
     versatile
    0.06
    Activations Density 0.073%

    No Known Activations