© 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. 124838
    Prev
    Next
    INDEX
    Explanations

    Hyphens and commas

    np_max-act · gemini-2.0-flash

    The neuron detects metadata fields in the document’s front-matter (e.g. keys like “ms.author,” “ms.date,” “ms.topic,” “service,” etc.).

    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
    otas
    -0.06
     OUT
    -0.06
    취
    -0.06
     CFG
    -0.06
     Atlantis
    -0.06
     آباد
    -0.06
     gap
    -0.06
     Gap
    -0.06
     Legendary
    -0.06
     zones
    -0.06
    POSITIVE LOGITS
    νώ
    0.07
     Ref
    0.06
    ({↵
    0.06
    рукт
    0.06
     ||
↵
    0.06
    Truthy
    0.06
    ับร
    0.06
     substantial
    0.06
     Kl
    0.06
     modest
    0.06
    Activations Density 0.010%

    No Known Activations