© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 54440
    Prev
    Next
    INDEX
    Explanations

    harmon

    np_max-act · gemini-2.0-flash

    This neuron responds to the special header‐related tokens (e.g. `<|start_header_id|>`) in the text.

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

    It detects mentions of the traditional Indian architectural/geomantic system and related discussion of its principles and practices.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    	board
    -0.07
     One
    -0.07
     Х
    -0.06
    _integral
    -0.06
    columnName
    -0.06
    }()↵
    -0.06
     đơn
    -0.06
     rolling
    -0.06
    (const
    -0.06
    Regardless
    -0.06
    POSITIVE LOGITS
    qd
    0.07
    ần
    0.07
    agal
    0.07
     artículo
    0.07
     Sq
    0.06
    ůže
    0.06
     beats
    0.06
    ourses
    0.06
    ضاء
    0.06
    след
    0.06
    Activations Density 0.200%

    No Known Activations