© 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. 56258
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron responds to document markup and code‐block delimiters (e.g. header‐id markers, “<|start_header_id|>”, “begin”, “verbatim”, braces, etc.), effectively detecting the boundaries and formatting tokens of embedded code blocks.

    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
    َف
    -0.07
    	Camera
    -0.07
    ior
    -0.06
     レ
    -0.06
    Но
    -0.06
    irs
    -0.06
    -produ
    -0.06
    フォ
    -0.06
    едж
    -0.06
    ichel
    -0.06
    POSITIVE LOGITS
     Membership
    0.07
     cùng
    0.07
     una
    0.07
    arah
    0.06
    ==
    0.06
    .userInteractionEnabled
    0.06
     omn
    0.06
    ByUsername
    0.06
    ＝＝
    0.06
     Ελλά
    0.06
    Activations Density 0.020%

    No Known Activations