© 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. 72160
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash

    code snippets demonstrating usage of the range function in Python relative to list size.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects special formatting or control tokens that mark the beginnings and ends of document or header sections (e.g. “<|begin_of_text|>”, “<|start_header_id|>”, “<|end_header_id|>”).

    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
     cực
    -0.07
    andles
    -0.07
    ंटर
    -0.06
    view
    -0.06
    елов
    -0.06
     popover
    -0.06
     dp
    -0.06
    =.
    -0.06
    `
    -0.06
    بيرة
    -0.06
    POSITIVE LOGITS
     Reaction
    0.07
     Associated
    0.07
     Marks
    0.06
     lobbying
    0.06
    xFB
    0.06
    +A
    0.06
     mobs
    0.06
     Restart
    0.06
     dismissal
    0.06
     revise
    0.06
    Activations Density 0.013%

    No Known Activations