© 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. 7248
    Prev
    Next
    INDEX
    Explanations

    text

    np_max-act · gemini-2.0-flash

    The neuron fires on meta-prompting language describing prompt length or simplicity (e.g. mentions of “single word,” “emoji,” “simple prompts,” 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
     audience
    -0.06
    iciency
    -0.06
     Roles
    -0.06
    Meeting
    -0.06
     writings
    -0.06
    ute
    -0.06
     Rus
    -0.06
    Analysis
    -0.06
    Visitor
    -0.06
    _auc
    -0.06
    POSITIVE LOGITS
     Desc
    0.07
     afl
    0.07
    inburgh
    0.06
     {@
    0.06
    .parentNode
    0.06
    ‡
    0.06
     gonna
    0.06
     иг
    0.06
    _MODAL
    0.06
     spare
    0.06
    Activations Density 0.015%

    No Known Activations